🧑‍🔬 Anca Dragan

🏛️ Affiliations

🎓University of California, BerkeleyBerkeley · United States2016–2025 · 134 papersEmploymentcurrent🏢GoogleMountain View · United States2025 · 1 papercurrent🏢KaggleSan Francisco2025 · 1 papercurrent🎓Carnegie Mellon UniversityPittsburgh · United States2011–2022 · 34 papersEducation🎓Georgia Institute of TechnologyAtlanta · United States2016–2021 · 2 papers🎓Constructor UniversityBremen · GermanyEducation

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.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 (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 (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 ↗arXiv:2408.00118 · no summary yetGemma Team et al.2024 · 1,302 citations
2. Managing extreme AI risks amid rapid progress ↗Science · no summary yetYoshua Bengio et al.2024 · 382 citations
3. Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2arXiv:2408.05147Tom Lieberum, Senthooran Rajamanoharan, Arthur Conmy, et al.2024 · 115 citations
4. Automatically Auditing Large Language Models via Discrete OptimizationarXiv:2303.04381Erik Jones, Anca Dragan, Aditi Raghunathan, et al.2023 · 89 citations
5. Translating Neuralese ↗Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetJacob Andreas, Anca Dragan, Dan Klein2017 · 54 citations
6. Evaluating Frontier Models for Dangerous Capabilities ↗arXiv:2403.13793 · no summary yetMary Phuong et al.2024 · 36 citations
7. Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety ↗arXiv (Cornell University) · no summary yetTomek Korbak et al.2025 · 35 citations
8. Inferring Rewards from Language in Context ↗Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetJessy Lin et al.2022 · 31 citations
9. Learning to Model the World with Language ↗arXiv (Cornell University) · no summary yetJessy Lin et al.2023 · 19 citations
10. Confronting Reward Model Overoptimization with Constrained RLHF ↗arXiv (Cornell University) · no summary yetTed Moskovitz et al.2023 · 19 citations
11. Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations ↗arXiv:2311.05584 · no summary yetJoey Hong, Sergey Levine, Anca Dragan2023 · 15 citations
12. Adversaries Can Misuse Combinations of Safe Models ↗arXiv (Cornell University) · no summary yetErik Jones, Anca D. Dragan, Jacob Steinhardt2024 · 5 citations
13. Agnostic learning with unknown utilities ↗arXiv (Cornell University) · no summary yetKush Bhatia et al.2021 · 2 citations

🤝 Co-authors here

11 co-authors with a page, the most papers together first.

• Aditi Raghunathan
• Arthur Conmy
• Erik Jones
• Jacob Steinhardt
• Janos Kramar
• Lewis Smith
• Neel Nanda
• Rohin Shah
• Senthooran Rajamanoharan
• Tom Lieberum
• 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 →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/anca-dragan/