This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
robertzk
Posts
Sorted by New
21
SAEs (usually) Transfer Between Base and Chat Models
9d
0
18
Attention Output SAEs Improve Circuit Analysis
1mo
0
33
We Inspected Every Head In GPT-2 Small using SAEs So You Don’t Have To
5mo
0
28
Attention SAEs Scale to GPT-2 Small
6mo
0
35
Sparse Autoencoders Work on Attention Layer Outputs
6mo
3
29
Training Process Transparency through Gradient Interpretability: Early experiments on toy language models
1y
1
14
Getting up to Speed on the Speed Prior in 2022
2y
0
Wiki Contributions
Comments