moved BatchTopKSAE to dictionary.py #51
Open
Conversation
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
|
Did the same process for TopKSAE and MatryoshkaBatchTopKSAE classes. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
As mentioned by @adamkarvonen in #47 : "The topk saes are in the trainer class, which is unfortunately a break from the typical convention in this repo". I moved to BatchTopkSAE to its right place (dictionary.py). Also, in order to solve circular imports due to the facts that both dictionary.py and batch_top_k.py imports from trainer.py after my change, I moved set_decoder_norm_to_unit_norm to dictionary.py as it isn't used only in the training, but also in the inference stage.