--- title: "Arthur Conmy · University of Toronto — author profile and papers" description: "Arthur Conmy, University of Toronto: 3 papers on Elamur Research (2023–2024), h-index 5 — affiliations, topics, co-authors and who cites…" canonical: "https://research.elamur.ai/free/en/authors/arthur-conmy/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/arthur-conmy/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Arthur Conmy # Arthur Conmy Arthur Conmy has 3 papers in our library, in 2023–2024, most of them on [Interpretability](https://md.research.elamur.ai/free/en/topics/interpretability/); often with [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/). 3 papers in our library · 2023–2024 [OpenAlex](https://openalex.org/A5071070679) · [**h-index 5**](https://openalex.org/authors/A5071070679) · [33 works](https://openalex.org/works?filter=author.id:A5071070679) · [149 citations](https://openalex.org/works?filter=author.id:A5071070679&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 3 works in our library](https://md.research.elamur.ai/free/en/authors/arthur-conmy/#papers) · [🔗 Cited 697 times in our library](https://md.research.elamur.ai/free/en/authors/arthur-conmy/cited-by/) · [6 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #6076](https://md.research.elamur.ai/free/en/paper-stars/page/61/#star-6076) 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=Arthur+Conmy) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Arthur+Conmy) · [dblp](https://dblp.org/search?q=Arthur+Conmy) · [ACL Anthology](https://aclanthology.org/search/?q=Arthur+Conmy) ## Affiliations [🎓**Stanford University** Stanford · United States 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/stanford-university/) · [🎓**University of Toronto** Toronto · Canada 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/university-of-toronto/) · [🎓**University of Cambridge** Cambridge · United Kingdom 2021–2023 · 3 papers](https://md.research.elamur.ai/free/en/universities/university-of-cambridge/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed. ## Fields, topics and concepts Of its works in our library, with the number of works on each. 📚 Shelves 6 The field of science this work belongs to (OpenAlex fields).[Computer Science · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Computer Vision and Pattern Recognition · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Arts and Humanities · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Software · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/software/) 🧭 Topics 1 Research subjects and languages the work is about.[Interpretability · 1 work](https://md.research.elamur.ai/free/en/topics/interpretability/) 💡 Concepts 1 Key ideas and methods explained on our concept pages.[Lexicography · 1 work](https://md.research.elamur.ai/free/en/concepts/lexicography/) ## Works by year ### 2020s [**2024** 2 papers](https://md.research.elamur.ai/free/en/authors/arthur-conmy/year/2024/) · [**2023** 1 paper](https://md.research.elamur.ai/free/en/authors/arthur-conmy/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. **[Attribution Patching Outperforms Automated Circuit Discovery](https://md.research.elamur.ai/free/en/papers/syed-2023-attribution-patching-outperforms-automated-circuit/)** *(2023 · 81 citations)* Mechanistic interpretability tries to find circuits, which are small subgraphs of a network that account for a specific behavior. Automated tools such as ACDC rely on activation patching. That method needs an extra forward pass for each edge it tests, so it scales poorly to large models. 3. **[Improving Dictionary Learning with Gated Sparse Autoencoders](https://md.research.elamur.ai/free/en/papers/rajamanoharan-2024-improving-dictionary-learning-gated-sparse/)** *(2024 · 42 citations)* Sparse autoencoders (SAEs) are used to break language model activations into sparse combinations of interpretable directions. ## All works 9 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them. 1. **[Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small ↗](https://arxiv.org/abs/2211.00593) arXiv:2211.00593 · no summary yet**Kevin Wang et al.*2022 · 376 citations* 2. [**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/) 3. [**Attribution Patching Outperforms Automated Circuit Discovery arXiv:2310.10348**Aaquib Syed, Can Rager, Arthur Conmy*2023 · 81 citations*](https://md.research.elamur.ai/free/en/papers/syed-2023-attribution-patching-outperforms-automated-circuit/) 4. **[Chain-of-Thought Reasoning In The Wild Is Not Always Faithful ↗](https://arxiv.org/abs/2503.08679) arXiv:2503.08679 · no summary yet**Ivan Arcuschin et al.*2025 · 52 citations* 5. **[Thought Anchors: Which LLM Reasoning Steps Matter? ↗](https://arxiv.org/abs/2506.19143) arXiv:2506.19143 · no summary yet**Paul C. Bogdan et al.*2025 · 44 citations* 6. [**Improving Dictionary Learning with Gated Sparse Autoencoders arXiv:2404.16014**Senthooran Rajamanoharan, Arthur Conmy, Lewis Smith, et al.*2024 · 42 citations*](https://md.research.elamur.ai/free/en/papers/rajamanoharan-2024-improving-dictionary-learning-gated-sparse/) 7. **[Successor Heads: Recurring, Interpretable Attention Heads In The Wild ↗](https://arxiv.org/abs/2312.09230) arXiv:2312.09230 · no summary yet**Rhys Gould et al.*2023 · 39 citations* 8. **[Copy Suppression: Comprehensively Understanding an Attention Head ↗](https://arxiv.org/abs/2310.04625) arXiv:2310.04625 · no summary yet**Callum McDougall et al.*2023 · 25 citations* 9. **[AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors ↗](https://arxiv.org/abs/2602.22755) arXiv (Cornell University) · no summary yet**Abhay Sheshadri et al.*2026 · 6 citations* ## Co-authors here 10 co-authors with a page, the most papers together first. - [Janos Kramar](https://md.research.elamur.ai/free/en/authors/janos-kramar/) ×2 - [Lewis Smith](https://md.research.elamur.ai/free/en/authors/lewis-smith/) ×2 - [Neel Nanda](https://md.research.elamur.ai/free/en/authors/neel-nanda/) ×2 - [Rohin Shah](https://md.research.elamur.ai/free/en/authors/rohin-shah/) ×2 - [Senthooran Rajamanoharan](https://md.research.elamur.ai/free/en/authors/senthooran-rajamanoharan/) ×2 - [Tom Lieberum](https://md.research.elamur.ai/free/en/authors/tom-lieberum/) ×2 - [Vikrant Varma](https://md.research.elamur.ai/free/en/authors/vikrant-varma/) ×2 - [Aaquib Syed](https://md.research.elamur.ai/free/en/authors/aaquib-syed/) - [Anca Dragan](https://md.research.elamur.ai/free/en/authors/anca-dragan/) - [Can Rager](https://md.research.elamur.ai/free/en/authors/can-rager/) ## Cited by Papers of our library cite their works 697 times (of the 149,439 papers whose bibliographies we read); [132 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/arthur-conmy/cited-by/). Updated 2 November 2026