TomasD

Karma: 114

Toy Models of Feature Absorption in SAEs

chanind, hrdkbhatnagar, TomasD and Joseph Bloom

7 Oct 2024 9:56 UTC

49 points

8 comments10 min readLW link

[Paper] A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders

chanind, TomasD, hrdkbhatnagar and Joseph Bloom

25 Sep 2024 9:31 UTC

71 points

16 comments3 min readLW link

(arxiv.org)

TomasD’s Shortform

TomasD14 Mar 2024 15:03 UTC

1 point

0 comments1 min readLW link