Skip to content

Issues: apartresearch/Interpreting-Learned-Feedback-Patterns

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

7 Open 0 Closed
7 Open 0 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Enhance: Support training on different of activations between base and reward models.
#15 opened Apr 7, 2024 by amirabdullah19852020
@amirabdullah19852020
More data: Create two datasets optimized for Vader, and upload to datasets data
#14 opened Apr 7, 2024 by amirabdullah19852020
@amirabdullah19852020
More reward models: Train a DPO model and autoencoders for unalignment dataset. model
#13 opened Apr 7, 2024 by amirabdullah19852020
@amirabdullah19852020
More reward models: Create contrastive pairs dataset for unalignment dataset. data
#12 opened Apr 7, 2024 by amirabdullah19852020
More reward models: Create a contrastive pairs dataset for helpful / harmless data
#11 opened Apr 7, 2024 by amirabdullah19852020
@amirabdullah19852020
More reward models: Train a DPO model and autoencoders for hh-hrlf model
#10 opened Apr 7, 2024 by amirabdullah19852020
@amirabdullah19852020
Enhance: Integrate with SAELens for the sparse autoencoder training. enhancement New feature or request
#9 opened Apr 7, 2024 by amirabdullah19852020
@amirabdullah19852020
ProTip! Exclude everything labeled bug with -label:bug.