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

[Feature Request / Suggestion]: Is it possible to extend this to text embeddings? #181

Open
fblissjr opened this issue Aug 8, 2024 · 1 comment
Open

[Feature Request / Suggestion]: Is it possible to extend this to text embeddings? #181

fblissjr opened this issue Aug 8, 2024 · 1 comment
Assignees
@frankaging
Labels
enhancement New feature or request

Comments

@fblissjr
Copy link

fblissjr commented Aug 8, 2024

Suggestion / Feature Request

Been curious for awhile now, then moreso since reading Disentangling Dense Embeddings with Sparse Autoencoders (https://arxiv.org/html/2408.00657v2)

It looks like most of the ingredients in pyvene are here to to do this with text embeddings?
@fblissjr fblissjr added the enhancement New feature or request label Aug 8, 2024
@frankaging
Copy link
Collaborator

@fblissjr Yes! We recently released one SAE tutorials on hidden layers, not the embedding layers. But if you specify the component to be the embedding layer output, you could essentially replicate the results in this paper IIUC: https://github.com/stanfordnlp/pyvene/blob/main/tutorials/basic_tutorials/Sparse_Autoencoder.ipynb

@frankaging frankaging self-assigned this Aug 11, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@frankaging frankaging

Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@fblissjr @frankaging