Eric Michaud

ericjm's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 11 months ago

Open Problems in Mechanistic Interpretability

Paper • 2501.16496 • Published Jan 27 • 20

authored 4 papers over 1 year ago

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Paper • 2403.19647 • Published Mar 28, 2024 • 4

Opening the AI black box: program synthesis via mechanistic interpretability

Paper • 2402.05110 • Published Feb 7, 2024 • 2

Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

Paper • 2307.15217 • Published Jul 27, 2023 • 37

Not All Language Model Features Are Linear

Paper • 2405.14860 • Published May 23, 2024 • 40