Hacker News
points by krackers 1 day ago | 0 comments
You don't even need SAE for residual stream based steering, you can do so much more naively by just taking the average difference in activations of prompted vs. unprompted versions, then PCA to get a "control vector" that you can use to elicit the prompted behavior

https://vgel.me/posts/representation-engineering/

Aún no hay comentarios.
Hacker News