NLPExplorer
Papers
Venues
Authors
Authors Timeline
Field of Study
URLs
ACL N-gram Stats
TweeNLP
API
Team
FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Datasets Dependency
Seonglae Cho
|
Harryn Oh
|
Donghyun Lee
|
Luis Rodrigues Vieira
|
Andrew Bermingham
|
Ziad El Sayed
|
Paper Details:
Month: July
Year: 2025
Location: Vienna, Austria
Venue:
ACL |
WS |
Citations
URL
No Citations Yet
https://skylion007.github.io/
https://www
https://github.com/seonglae/FaithfulSAE
https://huggingface.co/datasets/Open-Orca/FLAN
https://huggingface.co/datasets/xzuyn/open-instruct-uncensored-alpaca
https://huggingface.co/datasets/aifeifei798/merged_uncensored_alpaca
https://huggingface.co/collections/seonglae/faithful-saes-67f3b25ff21a185017879b33
https://huggingface.co/collections/seonglae/faithful-dataset-67f3b21ff8fca56b87e5370f
Field Of Study