Seonglae Chowhich layer
- mlp
- residual
- embedding
Steering GPT-2-XL by adding an activation vector — LessWrong
Prompt given to the model[1]I hate you becauseGPT-2I hate you because you are the most disgusting thing I have ever seen. GPT-2 + "Love" vectorI hate…
https://www.lesswrong.com/posts/5spBue2z2tw4JuDCx/steering-gpt-2-xl-by-adding-an-activation-vector
Google DeepMind
We then vary the coefficient of the steering vector added and look at the Pareto frontier for different methods of adding activation vectors.
[Full Post] Progress Update #1 from the GDM Mech Interp Team — LessWrong
This is a series of snippets about the Google DeepMind mechanistic interpretability team's research into Sparse Autoencoders, that didn't meet our ba…
![[Full Post] Progress Update #1 from the GDM Mech Interp Team — LessWrong](https://www.notion.so/image/https%3A%2F%2Fres.cloudinary.com%2Flesswrong-2-0%2Fimage%2Fupload%2Fv1497915096%2Ffavicon_lncumn.ico?table=block&id=184c3c96-247d-80c6-9bd6-c4db97dc9f21&cache=v2)
https://www.lesswrong.com/posts/C5KAZQib3bzzpeyrg/progress-update-1-from-the-gdm-mech-interp-team-full-update
![[Full Post] Progress Update #1 from the GDM Mech Interp Team — LessWrong](https://www.notion.so/image/https%3A%2F%2Fres.cloudinary.com%2Flesswrong-2-0%2Fimage%2Fupload%2Ff_auto%2Cq_auto%2Fv1%2FmirroredImages%2FC5KAZQib3bzzpeyrg%2Furkzhkxl8td0ovllz8zz?table=block&id=184c3c96-247d-80c6-9bd6-c4db97dc9f21&cache=v2)