---
title: "Enhancing Automated Interpretability with Output-Centric Feature"
description: "They propose a two-sided evaluation. 72 references, cited by 12 papers here. Among them: 1."
authors: ["Yoav Gur-Arieh", "Roy Mayan", "Chen Agassy", "Atticus Geiger", "Mor Geva"]
year: 2025
venue: "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2025.acl-long.288/"
doi: "10.18653/v1/2025.acl-long.288"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/arieh-2025-enhancing-automated-interpretability-output-centric/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/arieh-2025-enhancing-automated-interpretability-output-centric/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/6/) / Enhancing Automated Interpretability with Output-Centric Feature Descriptions

# Enhancing Automated Interpretability with Output-Centric Feature Descriptions

**Authors:** Yoav Gur-Arieh, Roy Mayan, Chen Agassy, [Atticus Geiger](https://md.research.elamur.ai/free/en/authors/atticus-geiger/) and [Mor Geva](https://md.research.elamur.ai/free/en/authors/mor-geva/) · **Year:** 2025 · **Venue:** [Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.acl-long.288/) · [PDF](https://aclanthology.org/2025.acl-long.288.pdf) · [DOI 10.18653/v1/2025.acl-long.288](https://doi.org/10.18653/v1/2025.acl-long.288) · [OpenAlex](https://openalex.org/W4412945693)

**Citations:** 1 citations (OpenAlex, 2026-10-14) · [12](https://md.research.elamur.ai/free/en/papers/arieh-2025-enhancing-automated-interpretability-output-centric/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Automated interpretability pipelines usually label LLM features, such as neurons or SAE latents, by showing an explainer model the inputs that activate them most strongly (MaxAct). The authors argue that this approach is costly and incomplete, because a feature's role also depends on how it changes the model's predictions. They propose a two-sided evaluation. In the input-based test, an LLM writes texts that should or should not trigger the feature according to its description. In the output-based test, the description must pick out generations produced while that feature is steered. They also introduce two cheap output-centric labeling methods. VocabProj projects the feature onto the vocabulary through the unembedding head. TokenChange records which token probabilities shift most when the feature is amplified. They tested neuron and SAE features from residual and MLP layers of several LLMs. MaxAct generally wins on the input test but trails on the output test, and ensembles of all three methods perform best on both. This matters for steering, editing and unlearning, which need descriptions that reflect causal effects.

## Key points
- Three description methods are compared: MaxAct (input-centric), VocabProj (one matrix multiplication) and TokenChange (a few forward passes). The output-centric methods need at most two inference passes.
- VocabProj sometimes comes close to MaxAct on the input-based evaluation, so it can serve as a cheap substitute in some cases.
- Output-centric descriptions often abstract the input-centric ones. Combining both can reveal a new meaning, for example a feature promoting "war" in business or social contexts (bidding war, culture war).
- With Gemma-2 SAEs, prompts guided by output-centric descriptions revived features previously considered "dead":
  - Activation was achieved for 85 MLP SAE features (9.1%) and for 491 residual features (62%).
  - 73% of revivals came from a simple '\<BOS>' plus one sampled token prompt.
- Code and generated descriptions are released at github.com/yoavgur/Feature-Descriptions.
- Limitations noted by the authors:
  - The output-based evaluation is noisy.
  - Results are sensitive to the prompt.
  - The methods cannot describe concepts that are hard to express with vocabulary tokens, such as positional features.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works · [💻 Software](https://md.research.elamur.ai/free/en/shelves/computer-science/software/) · 92 works

🧭 Topics (1): [🔬 Interpretability](https://md.research.elamur.ai/free/en/topics/interpretability/) · 130 works

## Cite

Cite as: Yoav Gur-Arieh, Roy Mayan, Chen Agassy, Atticus Geiger and Mor Geva. 2025. Enhancing Automated Interpretability with Output-Centric Feature Descriptions. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{gurarieh2025enhancing,
  title = {{Enhancing Automated Interpretability with Output-Centric Feature Descriptions}},
  author = {Yoav Gur-Arieh, Roy Mayan, Chen Agassy, Atticus Geiger and Mor Geva},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.acl-long.288},
  url = {https://doi.org/10.18653/v1/2025.acl-long.288}
}
```

- [← previous Enhancing Arabic Automated Essay Scoring with Synthetic Data and Error Injection](https://md.research.elamur.ai/free/en/papers/qwaider-2025-enhancing-arabic-automated-essay-scoring/)
- [next → FinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and Challenging](https://md.research.elamur.ai/free/en/papers/tang-2025-financereasoning-benchmarking-financial-numerical-reasoning/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/6/)

## References

72 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Rohan Anil, Andrew M. Dai, Orhan Firat, Melvin Johnson, Dmitry Lepikhin, Alexandre Passos, Siamak Shakeri, Emanuel Taropa, Paige Bailey, Zhifeng Chen, Eric Chu, Jonathan H. Clark, Laurent El Shafey, Yanping Huang, Kathy Meier-Hellstern, Gaurav Mishra, Erica Moreira, Mark Omernick, Kevin Robinson, Se… — [PaLM 2 Technical Report](https://md.research.elamur.ai/free/en/papers/anil-2023-palm-2-technical-report/)
2. Omer Antverg and Yonatan Belinkov. 2022. On the pitfalls of analyzing individual neurons in language models. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Omer+Antverg+and+Yonatan+Belinkov%2E+2022%2E+On+the+pitfalls+of+analyzing+individual+neurons+in+language+models%2E+In+International+Conference+on+Learning+Representations%2E)
3. Daniel Balcells, Benjamin Lerner, Michael Oesterle, Ediz Ucar, and Stefan Heimersheim. 2024. Evolution of sae features across layers in llms. Preprint, arXiv:2410.08869. — [arXiv:2410.08869](https://arxiv.org/abs/2410.08869) [find](https://scholar.google.com/scholar?q=Daniel+Balcells%2C+Benjamin+Lerner%2C+Michael+Oesterle%2C+Ediz+Ucar%2C+and+Stefan+Heimersheim%2E+2024%2E+Evolution+of+sae+features+across+layers+in+llms%2E+Preprint%2C+arXiv%3A2410%2E08869%2E+%E2%80%94+%5BarXiv%3A2410%2E08869%5D%28https%3A%2F%2Fa)
4. Anthony Bau, Yonatan Belinkov, Hassan Sajjad, Nadir Durrani, Fahim Dalvi, and James Glass. 2019. Identifying and controlling important neurons in neural machine translation. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Anthony+Bau%2C+Yonatan+Belinkov%2C+Hassan+Sajjad%2C+Nadir+Durrani%2C+Fahim+Dalvi%2C+and+James+Glass%2E+2019%2E+Identifying+and+controlling+important+neurons+in+neural+machine+translation%2E+In+International+Conferenc)
5. Usha Bhalla, Suraj Srinivas, Asma Ghandeharioun, and Himabindu Lakkaraju. 2024. Towards unifying interpretability and control: Evaluation via intervention. Preprint, arXiv:2411.04430. — [arXiv:2411.04430](https://arxiv.org/abs/2411.04430) [find](https://scholar.google.com/scholar?q=Usha+Bhalla%2C+Suraj+Srinivas%2C+Asma+Ghandeharioun%2C+and+Himabindu+Lakkaraju%2E+2024%2E+Towards+unifying+interpretability+and+control%3A+Evaluation+via+intervention%2E+Preprint%2C+arXiv%3A2411%2E04430%2E+%E2%80%94+%5BarXiv%3A2411%2E04)
6. Steven Bills, Nick Cammarata, Dan Mossing, Henk Tillman, Leo Gao, Gabriel Goh, Ilya Sutskever, Jan Leike, Jeff Wu, and William Saunders. 2023. Language models can explain neurons in language models. URL [https://openaipublic.blob](https://openaipublic.blob). core. windows. net/neuron-explainer/paper/index. html.(Date accessed:… [↗](https://openaipublic.blob)
7. J Bloom and J Lin. 2024. Understanding sae features with the logit lens. In AI Alignment Forum. [find](https://scholar.google.com/scholar?q=J+Bloom+and+J+Lin%2E+2024%2E+Understanding+sae+features+with+the+logit+lens%2E+In+AI+Alignment+Forum%2E)
8. Tolga Bolukbasi, Adam Pearce, Ann Yuan, Andy Coenen, Emily Reif, Fernanda Viégas, and Martin Wattenberg. 2021. An interpretability illusion for bert. Preprint, arXiv:2104.07143. — [arXiv:2104.07143](https://arxiv.org/abs/2104.07143) [find](https://scholar.google.com/scholar?q=Tolga+Bolukbasi%2C+Adam+Pearce%2C+Ann+Yuan%2C+Andy+Coenen%2C+Emily+Reif%2C+Fernanda+Vi%C3%A9gas%2C+and+Martin+Wattenberg%2E+2021%2E+An+interpretability+illusion+for+bert%2E+Preprint%2C+arXiv%3A2104%2E07143%2E+%E2%80%94+%5BarXiv%3A2104%2E07143%5D%28h)
9. Trenton Bricken, Adly Templeton, Joshua Batson, Brian Chen, Adam Jermyn, Tom Conerly, Nick Turner, Cem Anil, Carson Denison, Amanda Askell, Robert Lasenby, Yifan Wu, Shauna Kravec, Nicholas Schiefer, Tim Maxwell, Nicholas Joseph, Zac Hatfield-Dodds, Alex Tamkin, Karina Nguyen, Brayden McLean, Josiah… [find](https://scholar.google.com/scholar?q=Trenton+Bricken%2C+Adly+Templeton%2C+Joshua+Batson%2C+Brian+Chen%2C+Adam+Jermyn%2C+Tom+Conerly%2C+Nick+Turner%2C+Cem+Anil%2C+Carson+Denison%2C+Amanda+Askell%2C+Robert+Lasenby%2C+Yifan+Wu%2C+Shauna+Kravec%2C+Nicholas+Schiefer%2C+)
10. Gonçalo Paulo Caden Juang, Jacob Drori, and Nora Belrose. 2024. Open source automated interpretability for sparse autoencoder features. EleutherAI Blog, July, 30. [find](https://scholar.google.com/scholar?q=Gon%C3%A7alo+Paulo+Caden+Juang%2C+Jacob+Drori%2C+and+Nora+Belrose%2E+2024%2E+Open+source+automated+interpretability+for+sparse+autoencoder+features%2E+EleutherAI+Blog%2C+July%2C+30%2E)
11. Nitay Calderon, Roi Reichart, and Rotem Dror. 2025. [The alternative annotator test for llm-as-a-judge: How to statistically justify replacing human annotators with llms](https://md.research.elamur.ai/free/en/papers/calderon-2025-alternative-annotator-test-llm-as/). Preprint, arXiv:2501.10970.
12. Sviatoslav Chalnev, Matthew Siu, and Arthur Conmy. 2024. Improving steering vectors by targeting sparse autoencoder features. Preprint, arXiv:2411.02193. — [arXiv:2411.02193](https://arxiv.org/abs/2411.02193) [find](https://scholar.google.com/scholar?q=Sviatoslav+Chalnev%2C+Matthew+Siu%2C+and+Arthur+Conmy%2E+2024%2E+Improving+steering+vectors+by+targeting+sparse+autoencoder+features%2E+Preprint%2C+arXiv%3A2411%2E02193%2E+%E2%80%94+%5BarXiv%3A2411%2E02193%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F241)
13. Dami Choi, Vincent Huang, Kevin Meng, Daniel D Johnson, Jacob Steinhardt, and Sarah Schwettmann. 2024. Scaling automatic neuron description. [https://transluce.org/neuron-descriptions](https://transluce.org/neuron-descriptions). [↗](https://transluce.org/neuron-descriptions)
14. Roi Cohen, Eden Biran, Ori Yoran, Amir Globerson, and Mor Geva. 2024. Evaluating the ripple effects of knowledge editing in language models. Transactions of the Association for Computational Linguistics, 12:283–298. [find](https://scholar.google.com/scholar?q=Roi+Cohen%2C+Eden+Biran%2C+Ori+Yoran%2C+Amir+Globerson%2C+and+Mor+Geva%2E+2024%2E+Evaluating+the+ripple+effects+of+knowledge+editing+in+language+models%2E+Transactions+of+the+Association+for+Computational+Linguisti)
15. Róbert Csordás, Christopher Potts, Christopher D Manning, and Atticus Geiger. 2024. Recurrent neural networks learn to store and generate sequences using non-linear representations. In Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, pages 248–262, Mia… [find](https://scholar.google.com/scholar?q=R%C3%B3bert+Csord%C3%A1s%2C+Christopher+Potts%2C+Christopher+D+Manning%2C+and+Atticus+Geiger%2E+2024%2E+Recurrent+neural+networks+learn+to+store+and+generate+sequences+using+non%2Dlinear+representations%2E+In+Proceedings+of+)
16. Hoagy Cunningham, Aidan Ewart, Logan Riggs, Robert Huben, and Lee Sharkey. 2023. Sparse autoencoders find highly interpretable features in language models. arXiv preprint arXiv:2309.08600. [find](https://scholar.google.com/scholar?q=Hoagy+Cunningham%2C+Aidan+Ewart%2C+Logan+Riggs%2C+Robert+Huben%2C+and+Lee+Sharkey%2E+2023%2E+Sparse+autoencoders+find+highly+interpretable+features+in+language+models%2E+arXiv+preprint+arXiv%3A2309%2E08600%2E)
17. Damai Dai, Li Dong, Yaru Hao, Zhifang Sui, Baobao Chang, and Furu Wei. 2022. Knowledge neurons in pretrained transformers. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8493– 8502, Dublin, Ireland. Association for Computatio… [find](https://scholar.google.com/scholar?q=Damai+Dai%2C+Li+Dong%2C+Yaru+Hao%2C+Zhifang+Sui%2C+Baobao+Chang%2C+and+Furu+Wei%2E+2022%2E+Knowledge+neurons+in+pretrained+transformers%2E+In+Proceedings+of+the+60th+Annual+Meeting+of+the+Association+for+Computationa)
18. Fahim Dalvi, Nadir Durrani, Hassan Sajjad, Yonatan Belinkov, Anthony Bau, and James R. Glass. 2018. What is one grain of sand in the desert? analyzing individual neurons in deep nlp models. CoRR, abs/1812.09355. — [arXiv:1812.09355](https://arxiv.org/abs/1812.09355) [find](https://scholar.google.com/scholar?q=Fahim+Dalvi%2C+Nadir+Durrani%2C+Hassan+Sajjad%2C+Yonatan+Belinkov%2C+Anthony+Bau%2C+and+James+R%2E+Glass%2E+2018%2E+What+is+one+grain+of+sand+in+the+desert%3F+analyzing+individual+neurons+in+deep+nlp+models%2E+CoRR%2C+abs%2F)
19. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
20. Eoin Farrell, Yeu-Tong Lau, and Arthur Conmy. 2024a. Applying sparse autoencoders to unlearn knowledge in language models. Preprint, arXiv:2410.19278. — [arXiv:2410.19278](https://arxiv.org/abs/2410.19278) [find](https://scholar.google.com/scholar?q=Eoin+Farrell%2C+Yeu%2DTong+Lau%2C+and+Arthur+Conmy%2E+2024a%2E+Applying+sparse+autoencoders+to+unlearn+knowledge+in+language+models%2E+Preprint%2C+arXiv%3A2410%2E19278%2E+%E2%80%94+%5BarXiv%3A2410%2E19278%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2410%2E1)
21. Eoin Farrell, Yeu-Tong Lau, and Arthur Conmy. 2024b. Applying sparse autoencoders to unlearn knowledge in language models. arXiv preprint arXiv:2410.19278. — [arXiv:2410.19278](https://arxiv.org/abs/2410.19278) [find](https://scholar.google.com/scholar?q=Eoin+Farrell%2C+Yeu%2DTong+Lau%2C+and+Arthur+Conmy%2E+2024b%2E+Applying+sparse+autoencoders+to+unlearn+knowledge+in+language+models%2E+arXiv+preprint+arXiv%3A2410%2E19278%2E+%E2%80%94+%5BarXiv%3A2410%2E19278%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2)
22. Leo Gao, Stella Biderman, Sid Black, Laurence Golding, Travis Hoppe, Charles Foster, Jason Phang, Horace He, Anish Thite, Noa Nabeshima, Shawn Presser, and Connor Leahy. 2020. The pile: An 800gb dataset of diverse text for language modeling. Preprint, arXiv:2101.00027. [find](https://scholar.google.com/scholar?q=Leo+Gao%2C+Stella+Biderman%2C+Sid+Black%2C+Laurence+Golding%2C+Travis+Hoppe%2C+Charles+Foster%2C+Jason+Phang%2C+Horace+He%2C+Anish+Thite%2C+Noa+Nabeshima%2C+Shawn+Presser%2C+and+Connor+Leahy%2E+2020%2E+The+pile%3A+An+800gb+datas)
23. Leo Gao, Tom Dupré la Tour, Henk Tillman, Gabriel Goh, Rajan Troll, Alec Radford, Ilya Sutskever, Jan Leike, and Jeffrey Wu. 2024. Scaling and evaluating sparse autoencoders. Preprint, arXiv:2406.04093. [find](https://scholar.google.com/scholar?q=Leo+Gao%2C+Tom+Dupr%C3%A9+la+Tour%2C+Henk+Tillman%2C+Gabriel+Goh%2C+Rajan+Troll%2C+Alec+Radford%2C+Ilya+Sutskever%2C+Jan+Leike%2C+and+Jeffrey+Wu%2E+2024%2E+Scaling+and+evaluating+sparse+autoencoders%2E+Preprint%2C+arXiv%3A2406%2E0409)
24. Atticus Geiger, Duligur Ibeling, Amir Zur, Maheep Chaudhary, Sonakshi Chauhan, Jing Huang, Aryaman Arora, Zhengxuan Wu, Noah Goodman, Christopher Potts, and Thomas Icard. 2024a. Causal abstraction: A theoretical foundation for mechanistic interpretability. Preprint, arXiv:2301.04709. [find](https://scholar.google.com/scholar?q=Atticus+Geiger%2C+Duligur+Ibeling%2C+Amir+Zur%2C+Maheep+Chaudhary%2C+Sonakshi+Chauhan%2C+Jing+Huang%2C+Aryaman+Arora%2C+Zhengxuan+Wu%2C+Noah+Goodman%2C+Christopher+Potts%2C+and+Thomas+Icard%2E+2024a%2E+Causal+abstraction%3A+A+)
25. Atticus Geiger, Zhengxuan Wu, Christopher Potts, Thomas Icard, and Noah D. Goodman. 2024b. Finding alignments between interpretable causal variables and distributed neural representations. In Causal Learning and Reasoning, 1-3 April 2024, Los Angeles, California, USA, volume 236 of Proceedings of Ma… [find](https://scholar.google.com/scholar?q=Atticus+Geiger%2C+Zhengxuan+Wu%2C+Christopher+Potts%2C+Thomas+Icard%2C+and+Noah+D%2E+Goodman%2E+2024b%2E+Finding+alignments+between+interpretable+causal+variables+and+distributed+neural+representations%2E+In+Causal+L)
26. Mor Geva, Avi Caciularu, Guy Dar, Paul Roit, Shoval Sadde, Micah Shlain, Bar Tamir, and Yoav Goldberg. 2022a. LM-debugger: An interactive tool for inspection and intervention in transformer-based language models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processi… [find](https://scholar.google.com/scholar?q=Mor+Geva%2C+Avi+Caciularu%2C+Guy+Dar%2C+Paul+Roit%2C+Shoval+Sadde%2C+Micah+Shlain%2C+Bar+Tamir%2C+and+Yoav+Goldberg%2E+2022a%2E+LM%2Ddebugger%3A+An+interactive+tool+for+inspection+and+intervention+in+transformer%2Dbased+lang)
27. Mor Geva, Avi Caciularu, Kevin Wang, and Yoav Goldberg. 2022b. [Transformer feed-forward layers build predictions by promoting concepts in the vocabulary space](https://md.research.elamur.ai/free/en/papers/geva-2022-transformer-feed-forward-layers-build/). In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 30–45, Abu Dhabi, United Arab Emirates. Ass…
28. Mor Geva, Roei Schuster, Jonathan Berant, and Omer Levy. 2021. Transformer feed-forward layers are key-value memories. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 5484–5495, Online and Punta Cana, Dominican Republic. Association for Computational… [find](https://scholar.google.com/scholar?q=Mor+Geva%2C+Roei+Schuster%2C+Jonathan+Berant%2C+and+Omer+Levy%2E+2021%2E+Transformer+feed%2Dforward+layers+are+key%2Dvalue+memories%2E+In+Proceedings+of+the+2021+Conference+on+Empirical+Methods+in+Natural+Language+Pr)
29. Zhengfu He, Wentao Shu, Xuyang Ge, Lingjie Chen, Junxuan Wang, Yunhua Zhou, Frances Liu, Qipeng Guo, Xuanjing Huang, Zuxuan Wu, Yu-Gang Jiang, and Xipeng Qiu. 2024a. Llama scope: Extracting millions of features from llama-3.1-8b with sparse autoencoders. Preprint, arXiv:2410.20526. [find](https://scholar.google.com/scholar?q=Zhengfu+He%2C+Wentao+Shu%2C+Xuyang+Ge%2C+Lingjie+Chen%2C+Junxuan+Wang%2C+Yunhua+Zhou%2C+Frances+Liu%2C+Qipeng+Guo%2C+Xuanjing+Huang%2C+Zuxuan+Wu%2C+Yu%2DGang+Jiang%2C+and+Xipeng+Qiu%2E+2024a%2E+Llama+scope%3A+Extracting+millions+o)
30. Zhengfu He, Wentao Shu, Xuyang Ge, Lingjie Chen, Junxuan Wang, Yunhua Zhou, Frances Liu, Qipeng Guo, Xuanjing Huang, Zuxuan Wu, et al. 2024b. Llama scope: Extracting millions of features from llama-3.1-8b with sparse autoencoders. arXiv preprint arXiv:2410.20526. [find](https://scholar.google.com/scholar?q=Zhengfu+He%2C+Wentao+Shu%2C+Xuyang+Ge%2C+Lingjie+Chen%2C+Junxuan+Wang%2C+Yunhua+Zhou%2C+Frances+Liu%2C+Qipeng+Guo%2C+Xuanjing+Huang%2C+Zuxuan+Wu%2C+et+al%2E+2024b%2E+Llama+scope%3A+Extracting+millions+of+features+from+llama%2D3%2E)
31. Evan Hernandez, Sarah Schwettmann, David Bau, Teona Bagashvili, Antonio Torralba, and Jacob Andreas. 2022. Natural language descriptions of deep features. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Evan+Hernandez%2C+Sarah+Schwettmann%2C+David+Bau%2C+Teona+Bagashvili%2C+Antonio+Torralba%2C+and+Jacob+Andreas%2E+2022%2E+Natural+language+descriptions+of+deep+features%2E+In+International+Conference+on+Learning+Repre)
32. Jing Huang, Atticus Geiger, Karel D’Oosterlinck, Zhengxuan Wu, and Christopher Potts. 2023. [Rigorously assessing natural language explanations of neurons](https://md.research.elamur.ai/free/en/papers/huang-2023-rigorously-assessing-natural-language-explanations/). In Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, pages 317–331, Singapore. Association for Com…
33. Jing Huang, Zhengxuan Wu, Christopher Potts, Mor Geva, and Atticus Geiger. 2024. RAVEL: Evaluating interpretability methods on disentangling language model representations. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8669–… [find](https://scholar.google.com/scholar?q=Jing+Huang%2C+Zhengxuan+Wu%2C+Christopher+Potts%2C+Mor+Geva%2C+and+Atticus+Geiger%2E+2024%2E+RAVEL%3A+Evaluating+interpretability+methods+on+disentangling+language+model+representations%2E+In+Proceedings+of+the+62nd+)
34. Robert Huben, Hoagy Cunningham, Logan Riggs Smith, Aidan Ewart, and Lee Sharkey. 2024. Sparse autoencoders find highly interpretable features in language models. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Robert+Huben%2C+Hoagy+Cunningham%2C+Logan+Riggs+Smith%2C+Aidan+Ewart%2C+and+Lee+Sharkey%2E+2024%2E+Sparse+autoencoders+find+highly+interpretable+features+in+language+models%2E+In+The+Twelfth+International+Conferenc)
35. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, et al. 2024. [Gpt-4o system card](https://md.research.elamur.ai/free/en/papers/openai-2024-gpt-4o-system-card/). arXiv preprint arXiv:2410.21276.
36. Curt Tigges Joseph Bloom and David Chanin. 2024. Saelens. [https://github.com/jbloomAus/](https://github.com/jbloomAus/) SAELens. [↗](https://github.com/jbloomAus/)
37. Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B. Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. [Scaling laws for neural language models](https://md.research.elamur.ai/free/en/papers/kaplan-2020-scaling-laws-neural-language-models/). Preprint, arXiv:2001.08361.
38. Andrej Karpathy, Justin Johnson, and Li Fei-Fei. 2015. [Visualizing and understanding recurrent networks](https://md.research.elamur.ai/free/en/papers/karpathy-2015-visualizing-understanding-recurrent-networks/). arXiv preprint arXiv:1506.02078.
39. Dmitrii Kharlapenko, neverix, Neel Nanda, and Arthur Conmy. 2024. Self-explaining SAE features. [find](https://scholar.google.com/scholar?q=Dmitrii+Kharlapenko%2C+neverix%2C+Neel+Nanda%2C+and+Arthur+Conmy%2E+2024%2E+Self%2Dexplaining+SAE+features%2E)
40. Laura Kopf, Philine Lou Bommer, Anna Hedström, Sebastian Lapuschkin, Marina M. C. Höhne, and Kirill Bykov. 2024. Cosy: Evaluating textual explanations of neurons. Preprint, arXiv:2405.20331. — [arXiv:2405.20331](https://arxiv.org/abs/2405.20331) [find](https://scholar.google.com/scholar?q=Laura+Kopf%2C+Philine+Lou+Bommer%2C+Anna+Hedstr%C3%B6m%2C+Sebastian+Lapuschkin%2C+Marina+M%2E+C%2E+H%C3%B6hne%2C+and+Kirill+Bykov%2E+2024%2E+Cosy%3A+Evaluating+textual+explanations+of+neurons%2E+Preprint%2C+arXiv%3A2405%2E20331%2E+%E2%80%94+%5BarXiv%3A)
41. Quentin Lhoest, Albert Villanova del Moral, Yacine Jernite, Abhishek Thakur, Patrick von Platen, Suraj Patil, Julien Chaumond, Mariama Drame, Julien Plu, Lewis Tunstall, Joe Davison, Mario Šaško, Gunjan Chhablani, Bhavitvya Malik, Simon Brandeis, Teven Le Scao, Victor Sanh, Canwen Xu, Nicolas Patry,… — [Datasets: A Community Library for Natural Language Processing](https://md.research.elamur.ai/free/en/papers/lhoest-2021-datasets-community-library-natural-language/)
42. Kenneth Li, Oam Patel, Fernanda Viégas, Hanspeter Pfister, and Martin Wattenberg. 2023. [Inference-time intervention: Eliciting truthful answers from a language model](https://md.research.elamur.ai/free/en/papers/li-2023-inference-time-intervention-eliciting-truthful/). In Thirty-seventh Conference on Neural Information Processing Systems.
43. Tom Lieberum, Senthooran Rajamanoharan, Arthur Conmy, Lewis Smith, Nicolas Sonnerat, Vikrant Varma, Janos Kramar, Anca Dragan, Rohin Shah, and Neel Nanda. 2024. Gemma scope: Open sparse autoencoders everywhere all at once on gemma 2. In Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Inte… [find](https://scholar.google.com/scholar?q=Tom+Lieberum%2C+Senthooran+Rajamanoharan%2C+Arthur+Conmy%2C+Lewis+Smith%2C+Nicolas+Sonnerat%2C+Vikrant+Varma%2C+Janos+Kramar%2C+Anca+Dragan%2C+Rohin+Shah%2C+and+Neel+Nanda%2E+2024%2E+Gemma+scope%3A+Open+sparse+autoencoders+e)
44. Johnny Lin and Joseph Bloom. 2023. Neuronpedia: Interactive reference and tooling for analyzing neural networks with sparse autoencoders. Software available from neuronpedia.org. [find](https://scholar.google.com/scholar?q=Johnny+Lin+and+Joseph+Bloom%2E+2023%2E+Neuronpedia%3A+Interactive+reference+and+tooling+for+analyzing+neural+networks+with+sparse+autoencoders%2E+Software+available+from+neuronpedia%2Eorg%2E)
45. Aleksandar Makelov, Georg Lange, and Neel Nanda. 2024. Towards principled evaluations of sparse autoencoders for interpretability and control. In ICLR 2024 Workshop on Secure and Trustworthy Large Language Models. [find](https://scholar.google.com/scholar?q=Aleksandar+Makelov%2C+Georg+Lange%2C+and+Neel+Nanda%2E+2024%2E+Towards+principled+evaluations+of+sparse+autoencoders+for+interpretability+and+control%2E+In+ICLR+2024+Workshop+on+Secure+and+Trustworthy+Large+Lan)
46. Alireza Makhzani and Brendan Frey. 2014. k-sparse autoencoders. Preprint, arXiv:1312.5663. — [arXiv:1312.5663](https://arxiv.org/abs/1312.5663) [find](https://scholar.google.com/scholar?q=Alireza+Makhzani+and+Brendan+Frey%2E+2014%2E+k%2Dsparse+autoencoders%2E+Preprint%2C+arXiv%3A1312%2E5663%2E+%E2%80%94+%5BarXiv%3A1312%2E5663%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1312%2E5663%29)
47. Samuel Marks, Can Rager, Eric J. Michaud, Yonatan Belinkov, David Bau, and Aaron Mueller. 2024. Sparse feature circuits: Discovering and editing interpretable causal graphs in language models. Preprint, arXiv:2403.19647. [find](https://scholar.google.com/scholar?q=Samuel+Marks%2C+Can+Rager%2C+Eric+J%2E+Michaud%2C+Yonatan+Belinkov%2C+David+Bau%2C+and+Aaron+Mueller%2E+2024%2E+Sparse+feature+circuits%3A+Discovering+and+editing+interpretable+causal+graphs+in+language+models%2E+Preprin)
48. Samuel Marks, Can Rager, Eric J Michaud, Yonatan Belinkov, David Bau, and Aaron Mueller. 2025. Sparse feature circuits: Discovering and editing interpretable causal graphs in language models. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Samuel+Marks%2C+Can+Rager%2C+Eric+J+Michaud%2C+Yonatan+Belinkov%2C+David+Bau%2C+and+Aaron+Mueller%2E+2025%2E+Sparse+feature+circuits%3A+Discovering+and+editing+interpretable+causal+graphs+in+language+models%2E+In+The+T)
49. Tomás Mikolov, Ilya Sutskever, Kai Chen, Gregory S. Corrado, and Jeffrey Dean. 2013. [Distributed representations of words and phrases and their compositionality](https://md.research.elamur.ai/free/en/papers/mikolov-2013-distributed-representations-words-phrases-their/). In Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings…
50. Jesse Mu and Jacob Andreas. 2020. Compositional explanations of neurons. In Advances in Neural Information Processing Systems, volume 33, pages 17153– 17163. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Jesse+Mu+and+Jacob+Andreas%2E+2020%2E+Compositional+explanations+of+neurons%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+volume+33%2C+pages+17153%E2%80%93+17163%2E+Curran+Associates%2C+Inc%2E)
51. Aaron Mueller, Jannik Brinkmann, Millicent L. Li, Samuel Marks, Koyena Pal, Nikhil Prakash, Can Rager, Aruna Sankaranarayanan, Arnab Sen Sharma, Jiuding Sun, Eric Todd, David Bau, and Yonatan Belinkov. 2024. The quest for the right mediator: A history, survey, and theoretical grounding of causal int… — [arXiv:2408.01416](https://arxiv.org/abs/2408.01416) [find](https://scholar.google.com/scholar?q=Aaron+Mueller%2C+Jannik+Brinkmann%2C+Millicent+L%2E+Li%2C+Samuel+Marks%2C+Koyena+Pal%2C+Nikhil+Prakash%2C+Can+Rager%2C+Aruna+Sankaranarayanan%2C+Arnab+Sen+Sharma%2C+Jiuding+Sun%2C+Eric+Todd%2C+David+Bau%2C+and+Yonatan+Belinkov)
52. Seil Na, Yo Joong Choe, Dong-Hyun Lee, and Gunhee Kim. 2019. Discovery of natural language concepts in individual units of cnns. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Seil+Na%2C+Yo+Joong+Choe%2C+Dong%2DHyun+Lee%2C+and+Gunhee+Kim%2E+2019%2E+Discovery+of+natural+language+concepts+in+individual+units+of+cnns%2E+In+International+Conference+on+Learning+Representations%2E)
53. Neel Nanda and Joseph Bloom. 2022. Transformerlens. [https://github.com/TransformerLensOrg/](https://github.com/TransformerLensOrg/) TransformerLens. [↗](https://github.com/TransformerLensOrg/)
54. Nostalgebraist. 2020. interpreting GPT: the logit lens. [find](https://scholar.google.com/scholar?q=Nostalgebraist%2E+2020%2E+interpreting+GPT%3A+the+logit+lens%2E)
55. Kyle O’Brien, David Majercak, Xavier Fernandes, Richard Edgar, Jingya Chen, Harsha Nori, Dean Carignan, Eric Horvitz, and Forough Poursabzi-Sangde. 2024a. Steering language model refusal with sparse autoencoders. Preprint, arXiv:2411.11296. — [arXiv:2411.11296](https://arxiv.org/abs/2411.11296) [find](https://scholar.google.com/scholar?q=Kyle+O%E2%80%99Brien%2C+David+Majercak%2C+Xavier+Fernandes%2C+Richard+Edgar%2C+Jingya+Chen%2C+Harsha+Nori%2C+Dean+Carignan%2C+Eric+Horvitz%2C+and+Forough+Poursabzi%2DSangde%2E+2024a%2E+Steering+language+model+refusal+with+sparse+a)
56. Kyle O’Brien, David Majercak, Xavier Fernandes, Richard Edgar, Jingya Chen, Harsha Nori, Dean Carignan, Eric Horvitz, and Forough Poursabzi-Sangde. 2024b. Steering language model refusal with sparse autoencoders. arXiv preprint arXiv:2411.11296. — [arXiv:2411.11296](https://arxiv.org/abs/2411.11296) [find](https://scholar.google.com/scholar?q=Kyle+O%E2%80%99Brien%2C+David+Majercak%2C+Xavier+Fernandes%2C+Richard+Edgar%2C+Jingya+Chen%2C+Harsha+Nori%2C+Dean+Carignan%2C+Eric+Horvitz%2C+and+Forough+Poursabzi%2DSangde%2E+2024b%2E+Steering+language+model+refusal+with+sparse+a)
57. Kiho Park, Yo Joong Choe, Yibo Jiang, and Victor Veitch. 2024a. The geometry of categorical and hierarchical concepts in large language models. Preprint, arXiv:2406.01506. — [arXiv:2406.01506](https://arxiv.org/abs/2406.01506) [find](https://scholar.google.com/scholar?q=Kiho+Park%2C+Yo+Joong+Choe%2C+Yibo+Jiang%2C+and+Victor+Veitch%2E+2024a%2E+The+geometry+of+categorical+and+hierarchical+concepts+in+large+language+models%2E+Preprint%2C+arXiv%3A2406%2E01506%2E+%E2%80%94+%5BarXiv%3A2406%2E01506%5D%28https%3A%2F)
58. Kiho Park, Yo Joong Choe, and Victor Veitch. 2024b. [The linear representation hypothesis and the geometry of large language models](https://md.research.elamur.ai/free/en/papers/park-2023-linear-representation-hypothesis-geometry-large/). Preprint, arXiv:2311.03658.
59. Gonçalo Paulo, Alex Mallen, Caden Juang, and Nora Belrose. 2024. Automatically interpreting millions of features in large language models. Preprint, arXiv:2410.13928. — [arXiv:2410.13928](https://arxiv.org/abs/2410.13928) [find](https://scholar.google.com/scholar?q=Gon%C3%A7alo+Paulo%2C+Alex+Mallen%2C+Caden+Juang%2C+and+Nora+Belrose%2E+2024%2E+Automatically+interpreting+millions+of+features+in+large+language+models%2E+Preprint%2C+arXiv%3A2410%2E13928%2E+%E2%80%94+%5BarXiv%3A2410%2E13928%5D%28https%3A%2F%2Farxi)
60. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. 2019. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeffrey+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+Ilya+Sutskever%2C+et+al%2E+2019%2E+Language+models+are+unsupervised+multitask+learners%2E+OpenAI+blog%2C+1%288%29%3A9%2E)
61. Senthooran Rajamanoharan, Tom Lieberum, Nicolas Sonnerat, Arthur Conmy, Vikrant Varma, János Kramár, and Neel Nanda. 2024. Jumping ahead: Improving reconstruction fidelity with jumprelu sparse autoencoders. Preprint, arXiv:2407.14435. — [arXiv:2407.14435](https://arxiv.org/abs/2407.14435) [find](https://scholar.google.com/scholar?q=Senthooran+Rajamanoharan%2C+Tom+Lieberum%2C+Nicolas+Sonnerat%2C+Arthur+Conmy%2C+Vikrant+Varma%2C+J%C3%A1nos+Kram%C3%A1r%2C+and+Neel+Nanda%2E+2024%2E+Jumping+ahead%3A+Improving+reconstruction+fidelity+with+jumprelu+sparse+autoenc)
62. Nina Rimsky, Nick Gabrieli, Julian Schulz, Meg Tong, Evan Hubinger, and Alexander Turner. 2024. Steering llama 2 via contrastive activation addition. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15504–15522, Bangkok, Thaila… [find](https://scholar.google.com/scholar?q=Nina+Rimsky%2C+Nick+Gabrieli%2C+Julian+Schulz%2C+Meg+Tong%2C+Evan+Hubinger%2C+and+Alexander+Turner%2E+2024%2E+Steering+llama+2+via+contrastive+activation+addition%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+A)
63. Tamar Rott Shaham, Sarah Schwettmann, Franklin Wang, Achyuta Rajaram, Evan Hernandez, Jacob Andreas, and Antonio Torralba. 2024. A multimodal automated interpretability agent. In Forty-first International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Tamar+Rott+Shaham%2C+Sarah+Schwettmann%2C+Franklin+Wang%2C+Achyuta+Rajaram%2C+Evan+Hernandez%2C+Jacob+Andreas%2C+and+Antonio+Torralba%2E+2024%2E+A+multimodal+automated+interpretability+agent%2E+In+Forty%2Dfirst+Internati)
64. Chandan Singh, Aliyah R Hsu, Richard Antonello, Shailee Jain, Alexander G Huth, Bin Yu, and Jianfeng Gao. 2023. Explaining black box text modules in natural language with language models. arXiv preprint arXiv:2305.09863. — [arXiv:2305.09863](https://arxiv.org/abs/2305.09863) [find](https://scholar.google.com/scholar?q=Chandan+Singh%2C+Aliyah+R+Hsu%2C+Richard+Antonello%2C+Shailee+Jain%2C+Alexander+G+Huth%2C+Bin+Yu%2C+and+Jianfeng+Gao%2E+2023%2E+Explaining+black+box+text+modules+in+natural+language+with+language+models%2E+arXiv+prepri)
65. Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al. 2024a. [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://md.research.elamur.ai/free/en/papers/gemini-team-2024-gemini-1-5-unlocking-multimodal/). arXiv preprint arXiv:2403.05530.
66. Gemma Team, Morgane Riviere, Shreya Pathak, Pier Giuseppe Sessa, Cassidy Hardin, Surya Bhupatiraju, Léonard Hussenot, Thomas Mesnard, Bobak Shahriari, Alexandre Ramé, et al. 2024b. Gemma 2: Improving open language models at a practical size. arXiv preprint arXiv:2408.00118. [find](https://scholar.google.com/scholar?q=Gemma+Team%2C+Morgane+Riviere%2C+Shreya+Pathak%2C+Pier+Giuseppe+Sessa%2C+Cassidy+Hardin%2C+Surya+Bhupatiraju%2C+L%C3%A9onard+Hussenot%2C+Thomas+Mesnard%2C+Bobak+Shahriari%2C+Alexandre+Ram%C3%A9%2C+et+al%2E+2024b%2E+Gemma+2%3A+Improving+)
67. Adly Templeton, Tom Conerly, Jonathan Marcus, Jack Lindsey, Trenton Bricken, Brian Chen, Adam Pearce, Craig Citro, Emmanuel Ameisen, Andy Jones, Hoagy Cunningham, Nicholas L Turner, Callum McDougall, Monte MacDiarmid, C. Daniel Freeman, Theodore R. Sumers, Edward Rees, Joshua Batson, Adam Jermyn, Sh… [find](https://scholar.google.com/scholar?q=Adly+Templeton%2C+Tom+Conerly%2C+Jonathan+Marcus%2C+Jack+Lindsey%2C+Trenton+Bricken%2C+Brian+Chen%2C+Adam+Pearce%2C+Craig+Citro%2C+Emmanuel+Ameisen%2C+Andy+Jones%2C+Hoagy+Cunningham%2C+Nicholas+L+Turner%2C+Callum+McDougall%2C+)
68. Paul Upchurch, Jacob Gardner, Geoff Pleiss, Robert Pless, Noah Snavely, Kavita Bala, and Kilian Weinberger. 2017. Deep feature interpolation for image content changes. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 6090–6099. [find](https://scholar.google.com/scholar?q=Paul+Upchurch%2C+Jacob+Gardner%2C+Geoff+Pleiss%2C+Robert+Pless%2C+Noah+Snavely%2C+Kavita+Bala%2C+and+Kilian+Weinberger%2E+2017%2E+Deep+feature+interpolation+for+image+content+changes%2E+In+2017+IEEE+Conference+on+Compu)
69. Elena Voita, Javier Ferrando, and Christoforos Nalmpantis. 2024. Neurons in large language models: Dead, n-gram, positional. In Findings of the Association for Computational Linguistics: ACL 2024, pages 1288–1301, Bangkok, Thailand. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Elena+Voita%2C+Javier+Ferrando%2C+and+Christoforos+Nalmpantis%2E+2024%2E+Neurons+in+large+language+models%3A+Dead%2C+n%2Dgram%2C+positional%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL+2024%2C+pag)
70. T Wolf. 2019. [Huggingface’s transformers: State-ofthe-art natural language processing](https://md.research.elamur.ai/free/en/papers/wolf-2020-transformers-state-art-natural-language/). arXiv preprint arXiv:1910.03771.
71. Xinwei Wu, Junzhuo Li, Minghui Xu, Weilong Dong, Shuangzhi Wu, Chao Bian, and Deyi Xiong. 2023. DEPN: Detecting and editing privacy neurons in pre-trained language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 2875–2886, Singapore. Associati… [find](https://scholar.google.com/scholar?q=Xinwei+Wu%2C+Junzhuo+Li%2C+Minghui+Xu%2C+Weilong+Dong%2C+Shuangzhi+Wu%2C+Chao+Bian%2C+and+Deyi+Xiong%2E+2023%2E+DEPN%3A+Detecting+and+editing+privacy+neurons+in+pre%2Dtrained+language+models%2E+In+Proceedings+of+the+2023+C)
72. Alexander Yom Din, Taelin Karidi, Leshem Choshen, and Mor Geva. 2024. Jump to conclusions: Shortcutting transformers with linear transformations. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 9615–9… [find](https://scholar.google.com/scholar?q=Alexander+Yom+Din%2C+Taelin+Karidi%2C+Leshem+Choshen%2C+and+Mor+Geva%2E+2024%2E+Jump+to+conclusions%3A+Shortcutting+transformers+with+linear+transformations%2E+In+Proceedings+of+the+2024+Joint+International+Confere)

*Updated 31 October 2026*