Chasing the Counting Manifold in Open LLMs
📚
6
Counting manifolds in open LLMs from behavior to SAEs.
Alexey Gorbatovski
Myashka
AI & ML interests
NLP Alignment
Recent Activity
liked
a Space
about 5 hours ago
t-tech/manifolds
upvoted
a
paper
1 day ago
Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?
authored
a paper
11 days ago
F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare
Organizations
None yet
liked
a
Space
about 5 hours ago