RSS

Demian Till

Karma: 100

Bro­ken La­tents: Study­ing SAEs and Fea­ture Co-oc­cur­rence in Toy Models

chanind and Demian Till
30 Dec 2024 22:50 UTC
24 points
3 comments15 min readLW link

Do sparse au­toen­coders find “true fea­tures”?

Demian Till22 Feb 2024 18:06 UTC
76 points
33 comments11 min readLW link