SAELens
Autoencoder trainer
A tool for training and analyzing sparse autoencoders to improve the understanding of neural networks and create safer AI systems.
Training Sparse Autoencoders on Language Models
526 stars
7 watching
129 forks
Language: Jupyter Notebook
last commit: about 1 month ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 jakezhaojb/arae | An implementation of Adversarially Regularized Autoencoders for language generation and discrete structure modeling. | 400 |
 trungnt13/sisua | A software framework for semi-supervised generative Autoencoder models applied to single-cell data analysis. | 18 |
 intelligent-machine-learning/dlrover | Automates large-scale deep learning training on distributed clusters, providing fault tolerance and fast recovery from failures. | 1,302 |
 fducau/aae_pytorch | An implementation of Adversarial Autoencoders using PyTorch for training neural networks on structured data. | 199 |
 zhegan27/convsent | Trains an autoencoder to learn generic sentence representations using convolutional neural networks | 34 |
 eladhoffer/bigbatch | A tool for training neural networks using large batch sizes and analyzing the trade-offs between longer training periods and better generalization performance. | 148 |
 wojzaremba/algorithm-learning | A framework to learn simple algorithms from examples by generating and visualizing intermediate solutions | 180 |
 madebyollin/taesd | A Tiny AutoEncoder implementation for Stable Diffusion's image generation model | 602 |
 ahmedfgad/neuralgenetic | Trains artificial neural networks using the genetic algorithm | 241 |
 microsoft/mpnet | Develops a method for pre-training language understanding models by combining masked and permuted techniques, and provides code for implementation and fine-tuning. | 288 |
 shobrook/sequitur | A library of autoencoders for sequential data | 435 |
 madrylab/robustness | A library for training and evaluating neural networks with a focus on adversarial robustness. | 921 |
 fielddb/androidspeechrecognitiontrainer | An Android app for training speech recognition in low-resource languages, utilizing FieldDB corpora and user-defined vocabularies. | 3 |
| ahmedfgad/kerasga | Trains Keras models using the Genetic Algorithm | 36 |
| ahmedfgad/cnngenetic | Trains CNNs using a genetic algorithm for classification problems where one class per sample is allowed. | 22 |