#
attentionmech
Follow
Starred repositories
The nnsight package enables interpreting and manipulating the internals of deep learned models.
A roadmap for "generative AI" learning resources
Fast parallel LLM inference for MLX
The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…
The most cited deep learning papers
Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.
Implementation of papers in 100 lines of code.
Training Sparse Autoencoders on Language Models
A library for mechanistic interpretability of GPT-style language models
Mechanistic Interpretability in Transformers: This repository explores advanced techniques like Induction Head Detection and QK Circuit Analysis to uncover the inner workings of transformer-based m…
Sparse Autoencoder for Mechanistic Interpretability