Popular repositories Loading

1. [ICLR 23] A new framework to transform any neural networks into an interpretable concept-bottleneck-model (CBM) without needing labeled concept data

   Jupyter Notebook 145 36

2. [ICLR 23 spotlight] An automatic and efficient tool to describe functionalities of individual neurons in DNNs

   Jupyter Notebook 63 18

3. [NeurIPS 24] A new training and evaluation framework for learning interpretable deep vision models and benchmarking different interpretable concept-bottleneck-models (CBMs)

   Jupyter Notebook 36 7

4. [ICLR 25] A novel framework for building intrinsically interpretable LLMs with human-understandable concepts to ensure safety, reliability, transparency, and trustworthiness.

   Python 32 19

5. [CVPR 2025] Concept Bottleneck Autoencoder (CB-AE) -- efficiently transform any pretrained (black-box) image generative model into an interpretable generative concept bottleneck model (CBM) with mi…

   Jupyter Notebook 21 2

6. [EMNLP 25] An effective and interpretable weight-editing method for mitigating overly short reasoning in LLMs, and a mechanistic study uncovering how reasoning length is encoded in the model’s repr…

   Python 19 1