jbloomAus / SAELens

Training Sparse Autoencoders on Language Models
https://jbloomaus.github.io/SAELens/
MIT License
193 stars 67 forks source link

SAE steering vector tutorial #175

Closed NelsonG-C closed 3 weeks ago

NelsonG-C commented 3 weeks ago

Description

I have added a tutorial for sae steering vector. Note: I havent added it to the README as not all are listed there. I can add it there on a further commit if this is accepted without changes and should be added.

Type of change

Please delete options that are not relevant.

Checklist:

You have tested formatting, typing and unit tests (acceptance tests not currently in use)

jbloomAus commented 3 weeks ago

Thanks!