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

A library for making RepE control vectors

This repository collects all relevant resources about interpretability in LLMs

Implementation of the stacked denoising autoencoder in Tensorflow

Pytorch implementations of various types of autoencoders

SANSA - sparse EASE for millions of items

Evaluate interpretability methods on localizing and disentangling concepts in LLMs.

Tensorflow Examples

Sparse Auto Encoder and regular MNIST classification with mini batch's

Experiments with Adversarial Autoencoders using Keras

Multi-Layer Sparse Autoencoders

Repository of Deep Propensity Network - Sparse Autoencoder(DPN-SA) to calculate propensity score using sparse autoencoder

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"

Explore visualization tools for understanding Transformer-based large language models (LLMs)

Collection of autoencoder models in Tensorflow

A tiny easily hackable implementation of a feature dashboard.

Implemented semi-supervised learning for digit recognition using Sparse Autoencoder

A resource repository of sparse autoencoders for large language models

exploration WYSIWYG editor