Popular repositories Loading

1. ravel ravel Public

   Evaluate interpretability methods on localizing and disentangling concepts in LLMs.

   Python 20 2

2. eval_neuron_explanation eval_neuron_explanation Public

   A framework for evaluating natural language explanations of neurons.

   Python 1

3. char-iit char-iit Public

   A causal intervention framework to learn robust and interpretable character representations inside subword-based language models

   Jupyter Notebook