Skip to content

Pull requests: JoshEngels/MultiDimensionalFeatures

New pull request New
18 Open 3 Closed
18 Open 3 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
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Env var base dir
#25 opened Mar 13, 2026 by Tauheed-Elahee Loading…
Remove NVIDIA CUDA 12.1 hard pins from requirements
#24 opened Mar 13, 2026 by Tauheed-Elahee Loading…
Default cuda 0
#23 opened Mar 13, 2026 by Tauheed-Elahee Loading…
Bleeding Edge - Accept All Pull Requests
#22 opened Mar 13, 2026 by Tauheed-Elahee Loading…
1
Fix incorrect --clustering_type arg in README examples
#20 opened Mar 13, 2026 by Tauheed-Elahee Loading…
Add compatibility for newer sae_lens forward() return type
#19 opened Mar 13, 2026 by Tauheed-Elahee Loading…
Use dynamic device count instead of hardcoded num_devices=2
#18 opened Mar 13, 2026 by Tauheed-Elahee Loading…
Fix TransformerLens model name for GPT-2
#17 opened Mar 13, 2026 by Tauheed-Elahee Loading…
Update torch.load calls to include weights_only parameter
#16 opened Mar 12, 2026 by Tauheed-Elahee Loading…
legendHandles => legend_handles
#13 opened Sep 14, 2024 by JasonGross Loading…
1
Revert to cpu if cuda is not available (simpler version)
#11 opened Sep 9, 2024 by JasonGross Loading…
Add support for loading 16-bit models with --dtype
#10 opened Sep 9, 2024 by JasonGross Loading…
README: add some hyperlinks and code font
#9 opened Sep 7, 2024 by JasonGross Loading…
Fix some typos in README.md
#8 opened Sep 7, 2024 by JasonGross Loading…
Revert to cpu if cuda is not available (backwards compatible version)
#7 opened Sep 7, 2024 by JasonGross Loading…
Fix to better support MPS: convert to float32 earlier
#6 opened Sep 7, 2024 by JasonGross Loading…
Use pathlib more and have default cache paths be relative to the repo directory
#5 opened Sep 7, 2024 by JasonGross Loading…
Don't fail with "AssertionError: Not enough CUDA devices to support n_devices 2" when there aren't 2 GPUs
#4 opened Aug 28, 2024 by JasonGross Loading…
ProTip! What’s not been updated in a month: updated:<2026-02-24.