Arthur Conmy

~Arthur_Conmy1

9

论文总数

4.5

年均投稿

5.2

平均评分

接收情况4/9

会议分布

ICLR

6

ICML

2

NeurIPS

1

发表论文 (9 篇)

20256 篇

Applying Sparse Autoencoders to Unlearn Knowledge in Language Models

ICLR 2025Rejected

Scaling Sparse Feature Circuits For Studying In-Context Learning

ICML 2025Poster

Interpreting Attention Layer Outputs with Sparse Autoencoders

ICLR 2025Rejected

Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

ICLR 2025Rejected

Scaling Sparse Feature Circuits For Studying In-Context Learning

ICLR 2025Rejected

SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

ICML 2025Poster

20243 篇

Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders

NeurIPS 2024Poster

Copy Suppression: Comprehensively Understanding an Attention Head

ICLR 2024Rejected

Successor Heads: Recurring, Interpretable Attention Heads In The Wild

ICLR 2024Poster

合作者 (20)

Neel Nanda7 篇

Callum Stuart McDougall2 篇

Joseph Isaac Bloom2 篇

Janos Kramar2 篇

Senthooran Rajamanoharan2 篇

Tom Lieberum2 篇

Vikrant Varma2 篇

Dmitrii Kharlapenko2 篇