fix: warn rather than crash if sae is unnormalized#88
Merged
Conversation
chanind
force-pushed
the
allow-unnormalized-saes
branch
from
365b08d to
c154a4b
Compare
chanind
force-pushed
the
allow-unnormalized-saes
branch
from
c154a4b to
7aba53c
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Currently, SAEBench will error if an SAE is evaluated that does not have a unit-norm decoder. This makes it impossible to evaluate SAEs that cannot be normalized, for instance tied SAEs. This PR changes the error to a warning instead, so SAEs that cannot be easily normalized can still be evaluated in SAEBench.