wesg

Karma: 444

OR PhD student at MIT working on interpretability.

Find out more here: https://wesg.me/

Refusal in LLMs is mediated by a single direction

Andy Arditi, Oscar Obeso, Aaquib111, wesg and Neel Nanda

27 Apr 2024 11:13 UTC

228 points

93 comments10 min readLW link

SAE reconstruction errors are (empirically) pathological

wesg29 Mar 2024 16:37 UTC

105 points

16 comments8 min readLW link

Finding Neurons in a Haystack: Case Studies with Sparse Probing

wesg and Neel Nanda

3 May 2023 13:30 UTC

33 points

5 comments2 min readLW link

(arxiv.org)