Arthur Conmy

Identifiers

• name variant Arthur Conmy 0.60 · backfill

Papers (7)

1. How do LLMs Compute Verbal Confidence cs.CL · 2026 · author #2
2. Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities cs.CL · 2025 · author #3189
3. Open Problems in Mechanistic Interpretability cs.LG · 2025 · author #13
4. Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 cs.LG · 2024 · author #3
5. Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders cs.LG · 2024 · author #4
6. Improving Dictionary Learning with Gated Sparse Autoencoders cs.LG · 2024 · author #2
7. Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small cs.LG · 2022 · author #3

Mentions

• 2603.17839 #2 · arxiv_oai · confidence 0.70 Arthur Conmy
• 2404.16014 #2 · arxiv_oai · confidence 0.70 Arthur Conmy
• 2407.14435 #4 · arxiv_oai · confidence 0.70 Arthur Conmy

Frequent Coauthors

• Neel Nanda 4 shared papers
• J\'anos Kram\'ar 3 shared papers
• Rohin Shah 3 shared papers
• Senthooran Rajamanoharan 3 shared papers
• Tom Lieberum 3 shared papers
• Vikrant Varma 3 shared papers
• Anca Dragan 2 shared papers
• Lewis Smith 2 shared papers
• Nicolas Sonnerat 2 shared papers
• Petar Veli\v{c}kovi\'c 2 shared papers
• Simon Osindero 2 shared papers
• Viorica Patraucean 2 shared papers
• Aahil Mehta 1 shared papers
• Aaron Archer 1 shared papers
• Aaron Cohen 1 shared papers
• Aaron Parisi 1 shared papers
• Aaron Phillips 1 shared papers
• A\"aron van den Oord 1 shared papers
• Aarush Selvan 1 shared papers
• Aayush Singh 1 shared papers