Skip to content

Issues: bigscience-workshop/interpretability-ideas

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

10 Open 0 Closed
10 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

Implement the paper: https://arxiv.org/abs/nlin/0409024
#10 opened Feb 26, 2022 by oserikov
Research: probe for recursion in networks
#9 opened Feb 25, 2022 by oserikov
Allow to probe an arbitrary model's checkpoints with the off-the-shelf probes
#8 opened Feb 25, 2022 by oserikov
Provide the unified Interpretability API for both Huggingface and NON-Huggingface models
#7 opened Feb 25, 2022 by oserikov
Provide the unified interpretability cookbooks
#6 opened Feb 25, 2022 by oserikov
Implement the unified activations interpretation API for similar models
#5 opened Feb 24, 2022 by oserikov
Implement the unified attention interpretation API for similar models
#4 opened Feb 24, 2022 by oserikov
Integrate existing tools: Captum, LIT, AllenNLP Interpret, NeuroX into the HF pipeline
#3 opened Feb 24, 2022 by oserikov
Implement and perform the interpretability analysis of the BigScience models
#2 opened Feb 24, 2022 by oserikov
Imlement tests for abstract structures such as in Curcuits thread
#1 opened Feb 24, 2022 by oserikov
ProTip! What’s not been updated in a month: updated:<2024-10-06.