Skip to content

Visualizing the attention mechanism and exploring induction head behavior

Notifications You must be signed in to change notification settings

chenxcynthia/transformers

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

37 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Transformer interpretability research

Transformer models are improving at a rapid pace, making it of paramount importance to develop methods to explain, reverse-engineer, and visualize their inner workings. In this project, we study the interpretability of transformer models through a series of experiments divided into two parts:

  1. Visualizing Transformer Attention
  2. Exploring Induction Heads in BERT

This research was conducted as part of an independent study at the Harvard Insight and Interaction Lab under mentorship of Professor Martin Wattenberg, Professor Fernanda Viégas, and Catherine Yeh. The full write-up of this project can be found here.

About

Visualizing the attention mechanism and exploring induction head behavior

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published