--- title: "Anca Dragan — author profile and papers — Elamur Research" description: "Anca Dragan, Google: 2 papers on Elamur Research (2023–2024), h-index 50 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/anca-dragan/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/anca-dragan/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Anca Dragan # Anca Dragan Anca Dragan has 2 papers in our library, in 2023–2024, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/); often with [Aditi Raghunathan](https://md.research.elamur.ai/free/en/authors/aditi-raghunathan/), [Arthur Conmy](https://md.research.elamur.ai/free/en/authors/arthur-conmy/), [Erik Jones](https://md.research.elamur.ai/free/en/authors/erik-jones/). 2 papers in our library · 2023–2024 [OpenAlex](https://openalex.org/A5005997281) · [ORCID](https://orcid.org/0000-0001-6312-5466) · [Wikidata](https://www.wikidata.org/wiki/Q76514012) · [**h-index 50**](https://openalex.org/authors/A5005997281) · [209 works](https://openalex.org/works?filter=author.id:A5005997281) · [9,606 citations](https://openalex.org/works?filter=author.id:A5005997281&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/anca-dragan/#papers) · [🔗 Cited 1,523 times in our library](https://md.research.elamur.ai/free/en/authors/anca-dragan/cited-by/) · [11 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #6425](https://md.research.elamur.ai/free/en/paper-stars/page/65/#star-6425) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Anca+Dragan) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Anca+Dragan) · [dblp](https://dblp.org/search?q=Anca+Dragan) · [ACL Anthology](https://aclanthology.org/search/?q=Anca+Dragan) ## Affiliations [🎓**University of California, Berkeley** Berkeley · United States 2016–2025 · 134 papersEmployment*current*](https://md.research.elamur.ai/free/en/universities/university-of-california-berkeley/) · [🏢**Google** Mountain View · United States 2025 · 1 paper*current*](https://md.research.elamur.ai/free/en/companies/google/) · [🏢**Kaggle** San Francisco 2025 · 1 paper*current*](https://ror.org/050tqnp89) · [🎓**Carnegie Mellon University** Pittsburgh · United States 2011–2022 · 34 papersEducation](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) · [🎓**Georgia Institute of Technology** Atlanta · United States 2016–2021 · 2 papers](https://md.research.elamur.ai/free/en/universities/georgia-institute-of-technology/) · [🎓**Constructor University** Bremen · Germany Education](https://md.research.elamur.ai/free/en/universities/constructor-university/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 more institutions on single bylines are not listed. ## Fields, topics and concepts Of its works in our library, with the number of works on each. 📚 Shelves 7 The field of science this work belongs to (OpenAlex fields).[Computer Science · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Arts and Humanities · 1 work](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Safety Research · 1 work](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) · [Social Sciences · 1 work](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · [Computer Vision and Pattern Recognition · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Language and Linguistics · 1 work](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) 🧭 Topics 1 Research subjects and languages the work is about.[Language models & pretraining · 1 work](https://md.research.elamur.ai/free/en/topics/language-models/) ## Works by year ### 2020s [**2024** 1 paper](https://md.research.elamur.ai/free/en/authors/anca-dragan/year/2024/) · [**2023** 1 paper](https://md.research.elamur.ai/free/en/authors/anca-dragan/year/2023/) ## Papers The most cited first (OpenAlex and our library). 1. **[Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2](https://md.research.elamur.ai/free/en/papers/lieberum-2024-gemma-scope-open-sparse-autoencoders/)** *(2024 · 115 citations)* Sparse autoencoders (SAEs) break a language model's internal activations into many sparse, often human-interpretable directions. 2. **[Automatically Auditing Large Language Models via Discrete Optimization](https://md.research.elamur.ai/free/en/papers/jones-2023-automatically-auditing-large-language-models/)** *(2023 · 89 citations)* Testing language models for harmful or bizarre behavior before release is hard. Such failures can be rare, and people struggle to write the prompts that trigger them. Jones et al. treat auditing as a search problem. The auditor writes a scoring function over a prompt and its greedy completion, then looks for… ## All works 13 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them. 1. **[Gemma 2: Improving Open Language Models at a Practical Size ↗](https://arxiv.org/abs/2408.00118) arXiv:2408.00118 · no summary yet**Gemma Team et al.*2024 · 1,302 citations* 2. **[Managing extreme AI risks amid rapid progress ↗](https://doi.org/10.1126/science.adn0117) Science · no summary yet**Yoshua Bengio et al.*2024 · 382 citations* 3. [**Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 arXiv:2408.05147**Tom Lieberum, Senthooran Rajamanoharan, Arthur Conmy, et al.*2024 · 115 citations*](https://md.research.elamur.ai/free/en/papers/lieberum-2024-gemma-scope-open-sparse-autoencoders/) 4. [**Automatically Auditing Large Language Models via Discrete Optimization arXiv:2303.04381**Erik Jones, Anca Dragan, Aditi Raghunathan, et al.*2023 · 89 citations*](https://md.research.elamur.ai/free/en/papers/jones-2023-automatically-auditing-large-language-models/) 5. **[Translating Neuralese ↗](https://aclanthology.org/P17-1022/) Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Jacob Andreas, Anca Dragan, Dan Klein*2017 · 54 citations* 6. **[Evaluating Frontier Models for Dangerous Capabilities ↗](https://arxiv.org/abs/2403.13793) arXiv:2403.13793 · no summary yet**Mary Phuong et al.*2024 · 36 citations* 7. **[Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety ↗](https://arxiv.org/abs/2507.11473) arXiv (Cornell University) · no summary yet**Tomek Korbak et al.*2025 · 35 citations* 8. **[Inferring Rewards from Language in Context ↗](https://aclanthology.org/2022.acl-long.585/) Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Jessy Lin et al.*2022 · 31 citations* 9. **[Learning to Model the World with Language ↗](https://arxiv.org/abs/2308.01399) arXiv (Cornell University) · no summary yet**Jessy Lin et al.*2023 · 19 citations* 10. **[Confronting Reward Model Overoptimization with Constrained RLHF ↗](https://arxiv.org/abs/2310.04373) arXiv (Cornell University) · no summary yet**Ted Moskovitz et al.*2023 · 19 citations* 11. **[Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations ↗](https://arxiv.org/abs/2311.05584) arXiv:2311.05584 · no summary yet**Joey Hong, Sergey Levine, Anca Dragan*2023 · 15 citations* 12. **[Adversaries Can Misuse Combinations of Safe Models ↗](https://arxiv.org/abs/2406.14595) arXiv (Cornell University) · no summary yet**Erik Jones, Anca D. Dragan, Jacob Steinhardt*2024 · 5 citations* 13. **[Agnostic learning with unknown utilities ↗](https://arxiv.org/abs/2104.08482) arXiv (Cornell University) · no summary yet**Kush Bhatia et al.*2021 · 2 citations* ## Co-authors here 11 co-authors with a page, the most papers together first. - [Aditi Raghunathan](https://md.research.elamur.ai/free/en/authors/aditi-raghunathan/) - [Arthur Conmy](https://md.research.elamur.ai/free/en/authors/arthur-conmy/) - [Erik Jones](https://md.research.elamur.ai/free/en/authors/erik-jones/) - [Jacob Steinhardt](https://md.research.elamur.ai/free/en/authors/jacob-steinhardt/) - [Janos Kramar](https://md.research.elamur.ai/free/en/authors/janos-kramar/) - [Lewis Smith](https://md.research.elamur.ai/free/en/authors/lewis-smith/) - [Neel Nanda](https://md.research.elamur.ai/free/en/authors/neel-nanda/) - [Rohin Shah](https://md.research.elamur.ai/free/en/authors/rohin-shah/) - [Senthooran Rajamanoharan](https://md.research.elamur.ai/free/en/authors/senthooran-rajamanoharan/) - [Tom Lieberum](https://md.research.elamur.ai/free/en/authors/tom-lieberum/) - [Vikrant Varma](https://md.research.elamur.ai/free/en/authors/vikrant-varma/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) ×2 - Science ## Cited by Papers of our library cite their works 1,523 times (of the 149,439 papers whose bibliographies we read); [360 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/anca-dragan/cited-by/). Updated 2 November 2026