Skip to content
#

masking-experiments

Here is 1 public repository matching this topic...

Performed head-level interpretability analysis on Transformer models using masking experiments. Evaluated attention head contribution through accuracy and logit-based metrics (91% baseline accuracy).

  • Updated Feb 21, 2026
  • Jupyter Notebook

Improve this page

Add a description, image, and links to the masking-experiments topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the masking-experiments topic, visit your repo's landing page and select "manage topics."

Learn more