RSS

TomasD

Karma: 147

A Bunch of Ma­tryoshka SAEs

chanind, TomasD and Adrià Garriga-alonso
4 Apr 2025 14:53 UTC
29 points
0 comments8 min readLW link

Fea­ture Hedg­ing: Another way cor­re­lated fea­tures break SAEs

chanind, TomasD and Adrià Garriga-alonso
25 Mar 2025 14:33 UTC
22 points
0 comments18 min readLW link

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
73 points
16 comments3 min readLW link
(arxiv.org)

To­masD’s Shortform

TomasD14 Mar 2024 15:03 UTC
1 point
0 comments1 min readLW link