A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.

Implementation of the stacked denoising autoencoder in Tensorflow

Pivotal Token Search

Official Code for Paper: Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation

Pytorch implementations of various types of autoencoders

SANSA - sparse EASE for millions of items

Sparse Embedding Compression for Scalable Retrieval in Recommender Systems

Tensorflow Examples

Official Triton kernels for TopK and HierarchicalTopK Sparse Autoencoder decoders.

Multi-Layer Sparse Autoencoders (ICLR 2025)

Sparse Autoencoders (SAE) vs CLIP fine-tuning fun.

Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the paper "Evaluating Open-Source Sparse Autoencoders on Disentangling Factual Knowledge in GPT-2 Small"

[JAMIA] Official repository of Deep Propensity Network - Sparse Autoencoder(DPN-SA)

Interpret and control dense embedding via sparse autoencoder.

Repository for "From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance"

Collection of autoencoder models in Tensorflow

[NeurIPS 2025] This is the official repository for VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set

Implemented semi-supervised learning for digit recognition using Sparse Autoencoder

Implementations and Experiments: Transformers, RoPE, KV cache, SAEs, Tokenisers

Official code for NeurIPS 2025 paper "Revising and Falsifying Sparse Autoencoder Feature Explanations".