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
25
SAEs (usually) Transfer Between Base and Chat Models
2mo
0
18
Attention Output SAEs Improve Circuit Analysis
3mo
0
33
We Inspected Every Head In GPT-2 Small using SAEs So You Don’t Have To
6mo
0
28
Attention SAEs Scale to GPT-2 Small
7mo
0
35
Sparse Autoencoders Work on Attention Layer Outputs
8mo
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
Sorted by
Newest