Conversation
…n TransformerLensLanguageModel
…ntested) - Remove stateful `cache_activations` from `TransformerLensLanguageModel`, passing it as an argument instead to make the class stateless. - Remove the unused `initialize_replacement_model` method. - Add `column_id_to_info` method to map column IDs to specific feature, error, and embedding information. - Implement the core logic of the `attribute` method, including forward pass, building normalized edge matrix via gradient backpropagation, and feature attribution computation (tests not yet written).
…ibute implementation (untested) Add EdgeMatrix, a torch.Tensor wrapper subclass that carries cache_activations metadata through tensor operations. This simplifies the attribute method by encapsulating row/column info, activation lookups, and edge matrix construction into the class itself.
… SparseDictionaryConfig
…ry instead of AbstractSparseAutoEncoder
… and improve type hints
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No description provided.