codebert-head-interpretability

Interpreting and Validating Transformers for Source Code: Statistical, Structural, and Causal Analysis of Attention Heads in CodeBERT - A Research Endeavour

Name		Name	Last commit message	Last commit date
Latest commit History 79 Commits
head_analysis_go_outputs		head_analysis_go_outputs
head_analysis_java_outputs		head_analysis_java_outputs
head_analysis_javascript_outputs		head_analysis_javascript_outputs
head_analysis_python_outputs		head_analysis_python_outputs
head_analysis_ruby_outputs		head_analysis_ruby_outputs
notebooks		notebooks
src/codebert_head_interpretability		src/codebert_head_interpretability
templates		templates
tests/web		tests/web
.gitignore		.gitignore
.python-version		.python-version
Justfile		Justfile
README.md		README.md
main.py		main.py
pyproject.toml		pyproject.toml
uv.lock		uv.lock

Navigation Menu

Repository files navigation

codebert-head-interpretability

About

Releases

Packages

Contributors

Languages

Folders and files

Latest commit

History

Repository files navigation

codebert-head-interpretability

About

Resources

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages