Highlights
- Pro
Stars
16
stars
written in Jupyter Notebook
Clear filter
[NeurIPS 2020] Official code for the paper "DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation". Includes a PyTorch library for deep learning with SVG data.
Mechanistic Interpretability Visualizations using React
Steering Llama 2 with Contrastive Activation Addition
GLUCOSE: GeneraLized and COntextualized Story Explanations https://arxiv.org/abs/2009.07758
How do transformer LMs encode relations?
Code for reproducing our paper "Are Sparse Autoencoders Useful? A Case Study in Sparse Probing"