Skip to content

Issues: jbloomAus/SAELens

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

23 Open 97 Closed
23 Open 97 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

[Question] More information about the training process: hyperparameters and token number
#396 opened Dec 3, 2024 by TheMrguiller
6
[Bug Report] sh: trace trap error when trying to train an SAE
#392 opened Nov 30, 2024 by skunnavakkam
1 task done
1
[Bug Report] Unusual L0 Behavior with Gemma-2b
#382 opened Nov 22, 2024 by muyo8692
1 task done
[Proposal] Rename l1_coefficient to sparsity_coefficient
#360 opened Nov 4, 2024 by chanind
1 task done
1
1
Training time
#353 opened Oct 30, 2024 by merlinarer
1
[Proposal] Allow excluding special tokens when applying SAEs in HookedSAETransformer
#350 opened Oct 24, 2024 by chanind
1 task done
1
[Bug Report]
#337 opened Oct 18, 2024 by Yoon-Jeong-ho
6
[Proposal] Move files in tests/unit to tests
#335 opened Oct 17, 2024 by anthonyduong9
1 task done
1
[Proposal] BOS should be ignored by default in the activation store for SAEs not trained on the bos (and future SAEs trained in SAE Lens)
#333 opened Oct 16, 2024 by jbloomAus
1 task done
@chanind @curt-tigges
2
[Proposal] Make the SAE Lens API docs more comprehensive.
#319 opened Oct 4, 2024 by jbloomAus
[Bug Report] embedding layer models missing from canonical
#316 opened Oct 3, 2024 by dribnet
1
[Bug Report] Unable to train Mamba SAE
#311 opened Oct 1, 2024 by joelburget
1 task done
2
[Question] How to keep the consistency of ActivationStore
#297 opened Sep 21, 2024 by luckyeric320
[Proposal] Allow users to shuffle ActivationCache dataset, rather than shuffling the pieces of the activation cache
#277 opened Sep 3, 2024 by naterush
1 task done
2
[Bug Report] SAE training tutorial metrics do not match linked run
#276 opened Sep 3, 2024 by naterush
1 task done
3
[Bug Report] Log sparsity artifact seems wrong
#197 opened Jun 29, 2024 by ckkissane
2
[Bug Report] ActivationsStore fails for models without a tokenizer bug Something isn't working
#186 opened Jun 16, 2024 by chanind
1 task done
[Proposal] Add MLP transcoders
#182 opened Jun 15, 2024 by dtch1997
1 task done
1
1
[Proposal] tidy normalisation code
#151 opened May 15, 2024 by tomMcGrath
1 task done
[Proposal] We should make a more comprehensive / details contribution guide.
#149 opened May 15, 2024 by jbloomAus
Don't allow setting both d_sae and expansion_factor in config
#47 opened Mar 25, 2024 by chanind
1
4
Make a nicer config print output
#46 opened Mar 25, 2024 by jbloomAus
1
Support OthelloGPT enhancement New feature or request help wanted Extra attention is needed
#39 opened Mar 21, 2024 by jbloomAus
ProTip! Updated in the last three days: updated:>2025-01-07.