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] Add MLP transcoders #182

Open
1 task done
dtch1997 opened this issue Jun 15, 2024 · 1 comment · May be fixed by #183
Open
1 task done

[Proposal] Add MLP transcoders #182

dtch1997 opened this issue Jun 15, 2024 · 1 comment · May be fixed by #183

Comments

@dtch1997
Copy link
Contributor

Proposal

Support training, loading, and inference of MLP transcoders.

Motivation

MLP transcoders were trained by Jacob Dunefsky and Philippe Chlenski and have been shown to be useful.

Pitch

  • Implement a HookedTranscoder class analogous to HookedSAE and using similar functionality.
  • Implement a transcoder training runner.
  • Support loading pre-trained transcoder checkpoints.

Checklist

  • I have checked that there is no similar issue in the repo (required)
@dtch1997
Copy link
Contributor Author

I'm likely going to be rather hacky with the first pass of the implementation, and possibly duplicate a bunch of code in order to have maximum freedom to make changes. Refactoring can be done later.

@dtch1997 dtch1997 linked a pull request Jun 15, 2024 that will close this issue
Draft
13 tasks
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

Successfully merging a pull request may close this issue.

[WIP] feat: add mlp transcoders dtch1997/SAELens
1 participant
@dtch1997