| Name | Version | Summary | date |
| intel-ai-safety |
0.0.0 |
Explainable AI Tooling (XAI). XAI is used to discover and explain a model's prediction in a way that is interpretable to the user. Relevant information in the dataset, featureset, and model's algorithms are exposed. |
2024-04-23 02:52:49 |
| concept-erasure |
0.2.3 |
Erasing concepts from neural representations with provable guarantees |
2024-01-10 19:49:32 |
| osculari |
0.0.4 |
Open source library to explore artificial neural networks with psychophysical experiments. |
2023-12-21 20:31:42 |
| contrastive-xai |
0.1.1 |
Contrastive Explainable AI Algorithms |
2023-07-31 02:54:27 |
| eleuther-elk |
0.1.1 |
Keeping language models honest by directly eliciting knowledge encoded in their activations |
2023-07-20 23:32:21 |
| tuned-lens |
0.1.1 |
Tools for understanding how transformer predictions are built layer-by-layer |
2023-06-13 16:10:12 |
| time-interpret |
0.3.0 |
Model interpretability library for PyTorch with a focus on time series. |
2023-06-06 01:33:02 |