Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?
Paper
•
2602.14111
•
Published
•
51
Oleg Rogov
Olegario228
AI & ML interests
Reinforcement Learning, Neural Networks.
Recent Activity
authored
a paper
about 10 hours ago
Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?
Organizations
None yet
authored
a
paper
about 10 hours ago