RSS

Kola Ayonrinde

Karma: 13

In­ter­pretabil­ity as Com­pres­sion: Re­con­sid­er­ing SAE Ex­pla­na­tions of Neu­ral Ac­ti­va­tions with MDL-SAEs

Kola Ayonrinde, Michael Pearce and Lee Sharkey
23 Aug 2024 18:52 UTC
15 points
1 comment16 min readLW link