Skip to content

[Proposal] Direct Logit Attribution Tool #1263

@jlarson4

Description

@jlarson4

Proposal

PR #466 was created with the idea of adding a specific set of functions or utilities that could do the DLA process in a single call. The PR has been stale for two years now, but the idea behind it is sound.

Review the PR and create a new tool in transformer_lens/tools/analysis/direct_logit_attribution.py that handles this for the new TransformerBridge system.

Metadata

Metadata

Assignees

Labels

complexity-moderateModerately complicated issues for people who have intermediate experience with the codeenhancementNew feature or requestgood first issueGood for newcomershelp wantedExtra attention is neededminorRelease a minor version

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions