sparse-autoencoder

There are 2 repositories under sparse-autoencoder topic.

PaulPauls / llama3_interpretability_sae
A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.
feature-extraction feature-steering llama3 llm-interpretability open-research pytorch sparse-autoencoder
Language:Python 605
ruizheliUOA / Awesome-Interpretability-in-Large-Language-Models
This repository collects all relevant resources about interpretability in LLMs
dictionary-learning interpretability-and-explainability mechanistic-interpretability sparse-autoencoder
297
wblgers / tensorflow_stacked_denoising_autoencoder
Implementation of the stacked denoising autoencoder in Tensorflow
tensorflow autoencoder stacked-autoencoder denoising-autoencoders sparse-autoencoder
Language:Python 202
syorami / Autoencoders-Variants
Pytorch implementations of various types of autoencoders
pytorch autoencoder variational-autoencoder deep-learning sparse-autoencoder
Language:Python 67
glami / sansa
SANSA - sparse EASE for millions of items
approximate-inverse collaborative-filtering recommender-system sparse-autoencoder sparse-matrix
Language:Python 36
explanare / ravel
Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
causal-intervention disentangled-representations interpretability intervention probing sparse-autoencoder
Language:Python 34
khoink94 / tensorflow-Deep-learning
Tensorflow Examples
rbm grbm rnn brnn drnn cnn ae autoencoder sparseae sparse-autoencoder linear-regression logistic-regression multilayer-perceptron-network mlp mnist deep-learning machine-learning nearest-neighbors tf tensorflow
Language:Python 29
mrquincle / keras-adversarial-autoencoders
Experiments with Adversarial Autoencoders using Keras
jupyter sparse-autoencoder adversarial-autoencoder variational-autoencoder autoencoder keras
Language:Jupyter Notebook 22
snooky23 / K-Sparse-AutoEncoder
Sparse Auto Encoder and regular MNIST classification with mini batch's
sparse-autoencoder python3 deep-neural-networks pure-python mnist-dataset
Language:Jupyter Notebook 20
tim-lawson / mlsae
Multi-Layer Sparse Autoencoders
mechanistic-interpretability sae sparse-autoencoder transformer
Language:Python 12
shantanu-ai / DPN-SA
Repository of Deep Propensity Network - Sparse Autoencoder(DPN-SA) to calculate propensity score using sparse autoencoder
autoencoder sparse-autoencoder causal-inference causality dpn-sa deep-propensity-network deep-learning
Language:Python 10
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 8
Ki-Seki / Awesome-Transformer-Visualization
Explore visualization tools for understanding Transformer-based large language models (LLMs)
attention-mechanism awesome bert explainable-ai gemma interactive interactive-visualizations large-language-models llm mechanistic-interpretability sae sparse-autoencoder transformer visualization
7
ALPHAYA-Japan / autoencoders
Collection of autoencoder models in Tensorflow
autoencoder ae regularized-autoencoder sparse-autoencoder denoising-autoencoder vanilla-autoencoder stacked-autoencoder convolutional-autoencoder autoencoder-models vanilla tensorflow
Language:Python 5
Butanium / tiny-activation-dashboard
A tiny easily hackable implementation of a feature dashboard.
feature-visualization sparse-autoencoder sparse-autoencoders feature-dashboard
Language:Python 4
vivekamin / semi-supervised-learning
Implemented semi-supervised learning for digit recognition using Sparse Autoencoder
mnist-handwriting-recognition semi-supervised-learning sparse-autoencoder tensorflow
Language:Python 3
aarnphm / tinymorph
exploration WYSIWYG editor
capstone-project experimental interface mechanistic-interpretability sparse-autoencoder
Language:Jupyter Notebook 2
chrisliu298 / awesome-sparse-autoencoders
A resource repository of sparse autoencoders for large language models
large-language-model llm mechanistic-interpretability sparse-autoencoder
2
seonglae / emgsd-hermes
Steering GPT2-EMGSD less biased & Generating stereotyped text with vanilla GPT2 without fine tuning or prompt engineering
gpt2 sparse-autoencoder bias-correction bias-mitigation stereotype emgsd steering-vector
Language:Jupyter Notebook 2
sushantMoon / isi-nna
Neural Network Architcture | ISI Kolkata
cnn convolution lstm neural-network-architectures numpy pcan perceptron rnn sparse-autoencoder
Language:Jupyter Notebook 2
SayanChakraborty126 / ML-CODES
This repository contains Python codes for Autoenncoder, Sparse-autoencoder, HMM, Expectation-Maximization, Sum-product Algorithm, ANN, Disparity map, PCA.
ann autoenncoder disparity-map expectation-maximization machine-learning machine-learning-algorithms pca sparse-autoencoder sum-product sum-product-algorithm
Language:Jupyter Notebook 1
Specoptor / bot-iot
Implement a sparse autoencoder on the bot-iot dataset for dimensionality reduction followed by computation of reconstruction error, F1 score, recall, accuracy, weights, and threshold amongst other metrics
anomaly-detection deep-learning iot sparse-autoencoder
Language:Jupyter Notebook 0
sskrishn / Neural-Networks
Folder contains implementation of Multi layer feed forward networks, Autoencoders, Sparse Autoencoders and many..
autoencoder autoencoder-mnist backpropagation feedforward-neural-network mnist momentum neural-network regularization sparse-autoencoder sparse-autoencoders weight-decay
Language:HTML 0
cxcscmu / embedding-scope
Interpret and control dense embedding via sparse autoencoder.
embedding sparse-autoencoder
Language:Python
mcanalesmayo / SparseAutoencoder
Sparse Autoencoder based on the Unsupervised Feature Learning and Deep Learning tutorial from the Stanford University
deep-learning sparse-autoencoder unsupervised-learning
Language:Matlab

sparse-autoencoder

PaulPauls / llama3_interpretability_sae

ruizheliUOA / Awesome-Interpretability-in-Large-Language-Models

wblgers / tensorflow_stacked_denoising_autoencoder

syorami / Autoencoders-Variants

glami / sansa

explanare / ravel

khoink94 / tensorflow-Deep-learning

mrquincle / keras-adversarial-autoencoders

snooky23 / K-Sparse-AutoEncoder

tim-lawson / mlsae

shantanu-ai / DPN-SA

MaheepChaudhary / SAE-Ravel

Ki-Seki / Awesome-Transformer-Visualization

ALPHAYA-Japan / autoencoders

Butanium / tiny-activation-dashboard

vivekamin / semi-supervised-learning

aarnphm / tinymorph

chrisliu298 / awesome-sparse-autoencoders

seonglae / emgsd-hermes

sushantMoon / isi-nna

SayanChakraborty126 / ML-CODES

Specoptor / bot-iot

sskrishn / Neural-Networks

cxcscmu / embedding-scope

mcanalesmayo / SparseAutoencoder