Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, B…

A library for mechanistic interpretability of GPT-style language models

Training Sparse Autoencoders on Language Models

Mechanistic Interpretability Visualizations using React

Model interpretability and understanding for PyTorch

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

Lucid library adapted for PyTorch

Pytorch implementation of convolutional neural network visualization techniques

An interactive exploration of Transformer programming.

Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).