science-of-finetuning
Investigating the effect of finetuning on model internals.
Popular repositories Loading
-
crosscoder_learning
crosscoder_learning PublicForked from saprmarks/dictionary_learning
Modified to support crosscoder training.
-
sparsity-artifacts-crosscoders
sparsity-artifacts-crosscoders PublicCode for the "Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning" paper.
-
-
Repositories
Showing 4 of 4 repositories
- diffing-toolkit Public
science-of-finetuning/diffing-toolkit’s past year of commit activity - sparsity-artifacts-crosscoders Public
Code for the "Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning" paper.
science-of-finetuning/sparsity-artifacts-crosscoders’s past year of commit activity - crosscoder_learning Public Forked from saprmarks/dictionary_learning
Modified to support crosscoder training.
science-of-finetuning/crosscoder_learning’s past year of commit activity
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…