Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Proposal] Upload Steered Models to Huggingface Hub #407

Open
AMindToThink opened this issue Jan 18, 2025 · 0 comments
Open

[Proposal] Upload Steered Models to Huggingface Hub #407

AMindToThink opened this issue Jan 18, 2025 · 0 comments

Comments

@AMindToThink
Copy link

AMindToThink commented Jan 18, 2025 •
edited
Loading

It would be great if it were possible to steer models and upload them back to Huggingface as AutoModelForCausalLMs. For example, SAELens users should be able to make a dog-obsessed model by finding the dog feature and defining hooks that increase the feature during forward passes..

More people would make and use steered models, and it would be easier to import them and study them.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@AMindToThink