search

AlignmentResearch / tuned-lens

Tools for understanding how transformer predictions are built layer-by-layer
https://tuned-lens.readthedocs.io/en/latest/
MIT License
432 stars 47 forks source link

Logit lens #27

Closed levmckinney closed 1 year ago

levmckinney commented 1 year ago

Added an explicit logic lens class and improved the documentation of the tuned lens class. This should allow for the refactoring of several downstream functions like plot_tuned_lens.