This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
Yeu-Tong Lau
Posts
Sorted by New
Wikitag Contributions
Comments
Sorted by
Newest
82
SAEBench: A Comprehensive Benchmark for Sparse Autoencoders
Ω
9mo
Ω
6
43
Understanding Positional Features in Layer 0 SAEs
1y
0
17
An adversarial example for Direct Logit Attribution: memory management in gelu-4l
Ω
2y
Ω
0
Comments