Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Kola Ayonrinde
Karma:
32
All
Posts
Comments
New
Top
Old
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
39
points
5
comments
16
min read
LW
link
Back to top