open-research on Hacker News: 1 stories with screenshots

Screenshot of github.com: Show HN: Llama 3.2 Interpretability with Sparse Autoencoders

Show HN: Llama 3.2 Interpretability with Sparse Autoencoders (github.com)

542 points by PaulPauls 1 year ago | 80 comments

GitHub repository with an end-to-end PyTorch pipeline for LLM interpretability using sparse autoencoders on Llama 3.2, replicating Anthropic/OpenAI/DeepMind research.

sparse-autoencoders mechanistic-interpretability llama-3 pytorch

#open-research on Hacker News

Show HN: Llama 3.2 Interpretability with Sparse Autoencoders(github.com)

Show HN: Llama 3.2 Interpretability with Sparse Autoencoders (github.com)