Skip to content

abrvkh/explainability_toolkit

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Ana's Explainability Toolkit 🔎

A collection of methods to i) interpret deep neural network states (the decode folder) and ii) act on these interpretations (the act folder).

All methods rely on a model format similar to a HuggingFace🤗 model with the option to output_hidden_states = True to output the intermediate states and output_attentions=True to output attention maps.

The notebooks folder contains notebooks that show examples of how the methods can be used.

Decode

Act

Notebooks

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published