hrdkbhatnagar

(Not) Ex­plain­ing GPT-2-Small For­ward Passes with Edge-Level Au­toen­coder Circuits

Com­po­si­tion­al­ity and Am­bi­guity: La­tent Co-oc­cur­rence and In­ter­pretable Subspaces

Toy Models of Fea­ture Ab­sorp­tion in SAEs

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