---
title: "Atticus Geiger — all works — Elamur Research"
description: "All 30 works of Atticus Geiger in the Elamur Research library, the most cited first: our summaries where we have them, else the original."
canonical: "https://research.elamur.ai/free/en/authors/atticus-geiger/works/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/atticus-geiger/works/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Atticus Geiger](https://md.research.elamur.ai/free/en/authors/atticus-geiger/) / all works

# Atticus Geiger — all works

30 works · [← Atticus Geiger](https://md.research.elamur.ai/free/en/authors/atticus-geiger/)

1. **[Dynabench: Rethinking Benchmarking in NLP ↗](https://aclanthology.org/2021.naacl-main.324/) Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yet**Douwe Kiela et al.*2021 · 482 citations*
2. **[Causal Abstractions of Neural Networks ↗](https://arxiv.org/abs/2106.02997) arXiv:2106.02997 · no summary yet**Atticus Geiger et al.*2021 · 151 citations*
3. [**Neural Natural Language Inference Models Partially Embed Theories of Lexical Entailment and Negation**Atticus Geiger, Kyle Richardson, Christopher Potts*English · 123 citations*](https://md.research.elamur.ai/free/en/papers/geiger-2020-neural-natural-language-inference-models/)
4. **[DynaSent: A Dynamic Benchmark for Sentiment Analysis ↗](https://aclanthology.org/2021.acl-long.186/) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · no summary yet**Christopher Potts et al.*2021 · 103 citations*
5. [**Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations arXiv:2303.02536**Atticus Geiger, Zhengxuan Wu, Christopher Potts, et al.*2023 · 81 citations*](https://md.research.elamur.ai/free/en/papers/geiger-2023-finding-alignments-between-interpretable-causal/)
6. **[Interpretability at Scale: Identifying Causal Mechanisms in Alpaca](https://md.research.elamur.ai/free/en/papers/wu-2023-interpretability-scale-identifying-causal-mechanisms/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Zhengxuan Wu, Atticus Geiger, Thomas Icard, et al.*2023 · 81 citations*
7. **[ReFT: Representation Finetuning for Language Models](https://md.research.elamur.ai/free/en/papers/wu-2024-reft-representation-finetuning-language-models/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Zhengxuan Wu, Aryaman Arora, Zheng Wang, et al.*2024 · 74 citations*
8. **[Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability ↗](https://arxiv.org/abs/2301.04709) arXiv:2301.04709 · no summary yet**Atticus Geiger et al.*2023 · 65 citations*
9. [**Linear Representations of Sentiment in Large Language Models arXiv:2310.15154**Curt Tigges, Oskar John Hollinsworth, Atticus Geiger, et al.*2023 · 64 citations*](https://md.research.elamur.ai/free/en/papers/tigges-2023-linear-representations-sentiment-large-language/)
10. **[Posing Fair Generalization Tasks for Natural Language Inference](https://md.research.elamur.ai/free/en/papers/geiger-2019-posing-fair-generalization-tasks-natural/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Atticus Geiger, Ignacio Cases, Lauri Karttunen, et al.*2019 · 61 citations*
11. **[AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders ↗](https://arxiv.org/abs/2501.17148) arXiv:2501.17148 · no summary yet**Zhengxuan Wu et al.*2025 · 59 citations*
12. **[Inducing Causal Structure for Interpretable Neural Networks ↗](https://arxiv.org/abs/2112.00826) arXiv (Cornell University) · no summary yet**Atticus Geiger et al.*2021 · 53 citations*
13. **[RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations ↗](https://aclanthology.org/2024.acl-long.470/) Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Jing Huang et al.*2024 · 35 citations*
14. **[Rigorously Assessing Natural Language Explanations of Neurons](https://md.research.elamur.ai/free/en/papers/huang-2023-rigorously-assessing-natural-language-explanations/) [BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP](https://md.research.elamur.ai/free/en/venues/blackboxnlp/)**Jing Huang, Atticus Geiger, Karel D'Oosterlinck, et al.*2023 · 30 citations*
15. **[CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior ↗](https://arxiv.org/abs/2205.14140) arXiv (Cornell University) · no summary yet**Eldar David Abraham et al.*2022 · 29 citations*
16. **[ScoNe: Benchmarking Negation Reasoning in Language Models With Fine-Tuning and In-Context Learning ↗](https://aclanthology.org/2023.acl-short.154/) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · no summary yet**Jingyuan S. She et al.*2023 · 27 citations*
17. **[Causal Proxy Models for Concept-Based Model Explanations ↗](https://arxiv.org/abs/2209.14279) arXiv (Cornell University) · no summary yet**Zhengxuan Wu et al.*2022 · 27 citations*
18. **[pyvene: A Library for Understanding and Improving PyTorch Models via Interventions ↗](https://arxiv.org/abs/2403.07809) arXiv (Cornell University) · no summary yet**Zhengxuan Wu et al.*2024 · 26 citations*
19. **[Causal Distillation for Language Models ↗](https://aclanthology.org/2022.naacl-main.318/) Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yet**Zhengxuan Wu et al.*2022 · 25 citations*
20. **[Relational reasoning and generalization using nonsymbolic neural networks. ↗](https://doi.org/10.1037/rev0000371) Psychological Review · no summary yet**Atticus Geiger et al.*2020 · 19 citations*
21. **[Recursive Routing Networks: Learning to Compose Modules for Language Understanding ↗](https://aclanthology.org/N19-1365/) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · no summary yet**Ignacio Cases et al.*2019 · 19 citations*
22. **[Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations ↗](https://aclanthology.org/2024.blackboxnlp-1.17/) Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP · no summary yet**Róbert Csordás et al.*2024 · 16 citations*
23. **[Enhancing Automated Interpretability with Output-Centric Feature Descriptions](https://md.research.elamur.ai/free/en/papers/arieh-2025-enhancing-automated-interpretability-output-centric/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Yoav Gur-Arieh, Roy Mayan, Chen Agassy, et al.*2025 · 13 citations*
24. **[\textttpyvene: A Library for Understanding and Improving PyTorch Models via Interventions ↗](https://aclanthology.org/2024.naacl-demo.16/) Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: System Demonstrations) · no summary yet**Zhengxuan Wu et al.*2024 · 7 citations*
25. **[A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments ↗](https://arxiv.org/abs/2401.12631) arXiv (Cornell University) · no summary yet**Zhengxuan Wu et al.*2024 · 5 citations*
26. **[Updating CLIP to Prefer Descriptions Over Captions ↗](https://aclanthology.org/2024.emnlp-main.1125/) Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · no summary yet**Amir Zur et al.*2024 · 5 citations*
27. **[HyperSteer: Activation Steering at Scale with Hypernetworks ↗](https://arxiv.org/abs/2506.03292) arXiv (Cornell University) · no summary yet**Sun, Jiuding et al.*2025 · 4 citations*
28. **[HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks ↗](https://arxiv.org/abs/2503.10894) arXiv (Cornell University) · no summary yet**Jiuding Sun et al.*2025 · 4 citations*
29. **[Constructing Interpretable Features from Compositional Neuron Groups](https://md.research.elamur.ai/free/en/papers/shafran-2026-constructing-interpretable-features-compositional-neuron/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Or David Shafran, Atticus Geiger, Mor Geva*2026 · 1 citation*
30. **[Mechanistic interpretability and control for language models ↗](https://doi.org/10.25740/fg704nm2917) Stanford Digital Repository · no summary yet**Zhengxuan Wu et al.*2026*