Popular repositories Loading

1. ravel ravel Public

   Evaluate interpretability methods on localizing and disentangling concepts in LLMs.

   Jupyter Notebook 58 10

2. verbatim-memorization verbatim-memorization Public

   Demystifying Verbatim Memorization in Large Language Models

   Python 9 4

3. ood-prediction ood-prediction Public

   Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors

   Jupyter Notebook 6 1

4. char-iit char-iit Public

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

   Jupyter Notebook 3

5. eval-neuron-explanation eval-neuron-explanation Public

   A framework for evaluating auto-interp pipelines, i.e., natural language explanations of neurons.

   Python 3 1

6. predict_memorization predict_memorization Public

   Can we predict which sequences will be memorized by an LLM?

   Python 2 1