Peter Lai

Karma: 35

Mechanistic Interpretability Enthusiast

Proof-of-Concept Debugger for a Small LLM

Peter Lai and StefanHex

17 Mar 2025 22:27 UTC

27 points

0 comments11 min readLW link

SAE regularization produces more interpretable models

Peter Lai and StefanHex

28 Jan 2025 20:02 UTC

21 points

7 comments4 min readLW link

Peter Lai’s Shortform

Peter Lai25 Jan 2025 19:41 UTC

3 points

0 comments1 min readLW link