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
33
We Inspected Every Head In GPT-2 Small using SAEs So You Don’t Have To
1mo
0
28
Attention SAEs Scale to GPT-2 Small
3mo
0
35
Sparse Autoencoders Work on Attention Layer Outputs
3mo
3
29
Training Process Transparency through Gradient Interpretability: Early experiments on toy language models
9mo
1
14
Getting up to Speed on the Speed Prior in 2022
1y
0
Wiki Contributions
Comments