A library for making RepE control vectors

[UNMAINTAINED] 非监督特征学习与深度学习中文教程，该版本翻译自新版 UFLDL Tutorial 。建议新人们去学习斯坦福的CS231n课程，该门课程在网易云课堂上也有一个配有中文字幕的版本。

For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.

Finding Direction of arrival (DOA) of small UAVs using Sparse Denoising Autoencoders and Deep Neural Networks.

[ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers

Medical Imaging, Denoising Autoencoder, Sparse Denoising Autoencoder (SDAE) End-to-end and Layer Wise Pretraining

Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.

Sparse Autoencoders using FashionMNIST dataset

Hypothesizing interpretable relationships in text datasets using sparse autoencoders.

Hyperspectral Band Selection using Self-Representation Learning with Sparse 1D-Operational Autoencoder (SRL-SOA)

Implementation of PatchSAE as presented in "Sparse autoencoders reveal selective remapping of visual concepts during adaptation"

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"

A tiny easily hackable implementation of a feature dashboard.

Diagnóstico de falla de rodamiento utilizando descomposición modal empírica y deep learning

Use evolution with sparse autoencoders

Sparse Autoencoders (SAEs) for unsupervised music representation learning.

Implementation and analysis of Sparse Autoencoders for neural network interpretability research. Features interactive visualization dashboard and W&B integration.

CE-Bench: A Contrastive Evaluation Benchmark of LLM Interpretability with Sparse Autoencoders

A framework for conducting interpretability research and for developing an LLM from a synthetic dataset.

My AI interpretability research journey