sparse-autoencoders

There are 0 repository under sparse-autoencoders topic.

vgel / repeng
A library for making RepE control vectors
language-model machine-learning representation-engineering sae saes sparse-autoencoder sparse-autoencoders transformers
Language:Jupyter Notebook 568
ysh329 / Chinese-UFLDL-Tutorial
[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。
convolutional-neural-networks exercise sparse-autoencoders supervised-neural-network taught-learning unsupervised-learning
351
OpenMOSS / Language-Model-SAEs
For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.
interpretability mechanistic-interpretability sparse-autoencoders sparse-dictionary
Language:Python 146
LahiruJayasinghe / DeepDOA
Finding Direction of arrival (DOA) of small UAVs using Sparse Denoising Autoencoders and Deep Neural Networks.
autoencoder denoising-autoencoders direction-of-arrival sparse-autoencoders unmanned-aerial-vehicle
Language:Python 87
dmis-lab / Monet
[ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers
iclr iclr2025 interpretability large-language-models mixture-of-experts sparse-autoencoders
Language:Python 63
abhisheksambyal / Autoencoders-using-Pytorch-Medical-Imaging
Medical Imaging, Denoising Autoencoder, Sparse Denoising Autoencoder (SDAE) End-to-end and Layer Wise Pretraining
autoencoder-classification autoencoder-mnist autoencoder-pytorch autoencoder-segmentation autoencoders autoencoders-fashionmnist denoising-autoencoders sparse-autoencoders
Language:Jupyter Notebook 47
rmovva / HypotheSAEs
Hypothesizing interpretable relationships in text datasets using sparse autoencoders.
ai-for-science computational-social-science interpretability nlp sparse-autoencoders topic-modeling
Language:Jupyter Notebook 43
neuroexplicit-saar / Discover-then-Name
Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.
concept-bottleneck-models concept-extraction eccv2024 sparse-autoencoders
Language:Python 39
Abhipanda4 / Sparse-Autoencoders
Sparse Autoencoders using FashionMNIST dataset
pytorch autoencoders sparse-autoencoders fashion-mnist
Language:Python 35
meteahishali / SRL-SOA
Hyperspectral Band Selection using Self-Representation Learning with Sparse 1D-Operational Autoencoder (SRL-SOA)
band-selection machine-learning sparse-autoencoders 1d-operational-layers hyperspectral-images
Language:Python 22
MaheepChaudhary / SAE-Ravel
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"
sae sparse-autoencoder sparse-autoencoders
Language:Python 11
Butanium / tiny-activation-dashboard
A tiny easily hackable implementation of a feature dashboard.
feature-dashboard feature-visualization sparse-autoencoder sparse-autoencoders
Language:Jupyter Notebook 9
gkimer / thesis-ICI
Diagnóstico de falla de rodamiento utilizando descomposición modal empírica y deep learning
bearing-fault-diagnosis matlab emd dnn autoencoders sparse-autoencoders
Language:MATLAB 6
255BITS / sae-evolver
Use evolution with sparse autoencoders
evolutionary-algorithms python sparse-autoencoders
Language:Python 4
ashioyajotham / exploring_saes
Implementation and analysis of Sparse Autoencoders for neural network interpretability research. Features interactive visualization dashboard and W&B integration.
mech-interp neuron-activity wandb interpretability sparse-autoencoders activation-functions transformerlens
Language:Python 1
DanielJamesDavies / Turing-LLM-1.0-254M
A framework for conducting interpretability research and for developing an LLM from a synthetic dataset.
interpretability large-language-model mechanistic-interpretability python sparse-autoencoders
Language:Python 1
Yusen-Peng / KAN-LLaMA
KAN-LLaMA: An Interpretable Large Language Model With KAN-based Sparse Autoencoders
llm-interpretability sparse-autoencoders kolmogorov-arnold-networks
Language:HTML 1
ashioyajotham / interp
My AI interpretability research journey
interpretability mech-interp backpropagation sparse-autoencoders
Language:HTML 0
sskrishn / Neural-Networks
Folder contains implementation of Multi layer feed forward networks, Autoencoders, Sparse Autoencoders and many..
autoencoder-mnist backpropagation mnist feedforward-neural-network neural-network sparse-autoencoder regularization momentum weight-decay sparse-autoencoders autoencoder
Language:HTML 0
Utkarshp1 / EE-412-Neural-Networks-and-Deep-Learning
This repository is created as part of Neural Networks and Deep Learning course at my college. This repo contains the implementations of Neural Network and Deep Learning algorithms.
deep-learning deep-neural-networks deeplearning python3 neural-network neural-networks deep-learning-algorithms autoencoders cnn-keras convolutional-neural-networks tensorflow contractive-autonencoders sparse-autoencoders regularization-autoencoders weight-decay-autoencoder
Language:Jupyter Notebook 0
ghost1412 / Keras-Autoencoder
autoencoder deep-learning python keras-tensorflow variational-autoencoder sparse-autoencoders
Language:Python
martinkersner / autoencoder-meetup
Presentation about Autoencoders for Seoul AI Meetup on July 8, 2017.
autoencoder sparse-autoencoders tensorflow variational-autoencoders
Language:Jupyter Notebook

sparse-autoencoders

vgel / repeng

ysh329 / Chinese-UFLDL-Tutorial

OpenMOSS / Language-Model-SAEs

LahiruJayasinghe / DeepDOA

dmis-lab / Monet

abhisheksambyal / Autoencoders-using-Pytorch-Medical-Imaging

rmovva / HypotheSAEs

neuroexplicit-saar / Discover-then-Name

Abhipanda4 / Sparse-Autoencoders

meteahishali / SRL-SOA

MaheepChaudhary / SAE-Ravel

Butanium / tiny-activation-dashboard

gkimer / thesis-ICI

255BITS / sae-evolver

ashioyajotham / exploring_saes

DanielJamesDavies / Turing-LLM-1.0-254M

Yusen-Peng / KAN-LLaMA

ashioyajotham / interp

sskrishn / Neural-Networks

Utkarshp1 / EE-412-Neural-Networks-and-Deep-Learning

ghost1412 / Keras-Autoencoder

martinkersner / autoencoder-meetup