Comgra: A Tool for Analyzing and Debugging Neural Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910548813152256 |
|---|---|
| author | Dietz, Florian Fellenz, Sophie Klakow, Dietrich Kloft, Marius |
| author_facet | Dietz, Florian Fellenz, Sophie Klakow, Dietrich Kloft, Marius |
| contents | Neural Networks are notoriously difficult to inspect. We introduce comgra, an open source python library for use with PyTorch. Comgra extracts data about the internal activations of a model and organizes it in a GUI (graphical user interface). It can show both summary statistics and individual data points, compare early and late stages of training, focus on individual samples of interest, and visualize the flow of the gradient through the network. This makes it possible to inspect the model's behavior from many different angles and save time by rapidly testing different hypotheses without having to rerun it. Comgra has applications for debugging, neural architecture design, and mechanistic interpretability. We publish our library through Python Package Index (PyPI) and provide code, documentation, and tutorials at https://github.com/FlorianDietz/comgra. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_21656 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Comgra: A Tool for Analyzing and Debugging Neural Networks Dietz, Florian Fellenz, Sophie Klakow, Dietrich Kloft, Marius Machine Learning Neural Networks are notoriously difficult to inspect. We introduce comgra, an open source python library for use with PyTorch. Comgra extracts data about the internal activations of a model and organizes it in a GUI (graphical user interface). It can show both summary statistics and individual data points, compare early and late stages of training, focus on individual samples of interest, and visualize the flow of the gradient through the network. This makes it possible to inspect the model's behavior from many different angles and save time by rapidly testing different hypotheses without having to rerun it. Comgra has applications for debugging, neural architecture design, and mechanistic interpretability. We publish our library through Python Package Index (PyPI) and provide code, documentation, and tutorials at https://github.com/FlorianDietz/comgra. |
| title | Comgra: A Tool for Analyzing and Debugging Neural Networks |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2407.21656 |