Arthur Conmy

Thought Anchors: Which LLM Reasoning Steps Matter?

Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Base Models Know How to Reason, Thinking Models Learn When

Eliciting Secret Knowledge from Language Models

Fluid Reasoning Representations

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

Applying Sparse Autoencoders to Unlearn Knowledge in Language Models

Interpreting Attention Layer Outputs with Sparse Autoencoders

Scaling Sparse Feature Circuits For Studying In-Context Learning

Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Scaling Sparse Feature Circuits For Studying In-Context Learning