Closed jbloomAus closed 1 month ago
Attention: Patch coverage is 59.28500%
with 410 lines
in your changes are missing coverage. Please review.
Project coverage is 52.34%. Comparing base (
eb9489a
) to head (3faeae8
).
:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.
I'm leaving this here for a few hours while I dm some people for feedback. This will likely be merged shortly.
Description
In this PR, we support HookedSAETransformer (coming over from TransformerLens) and refactor a bunch of stuff internally. I'm sorry this PR is so large and for the number of breaking changes. I'm hoping that the future need for refactors is much smaller. We expect the changes to be fairly superficial / easy to adapt to except for those working on forks. Feel free to reach out for assistance / clarification if you are trying to update a fork. Finally, we think it's likely there are no major regressions or introduced bugs, but the test coverage now looks lower as we're showing over the entire repo and not just the training subpackage.
New Features:
SAE
notSAEConfig
.Breaking changes:
Features we removed:
Renaming:
Notes:
Type of change
Please delete options that are not relevant.
Checklist:
You have tested formatting, typing and unit tests (acceptance tests not currently in use)
make check-ci
to check format and linting. (you can runmake format
to format code if needed.)Performance Check.
If you have implemented a training change, please indicate precisely how performance changes with respect to the following metrics:
Please links to wandb dashboards with a control and test group.