VAEase Project

This repository contains code for experiments with various autoencoder models and synthetic datasets, as described in the associated paper.

File Overview

models.py
Contains the implementation of all model architectures used in the experiments, including encoders, decoders, and other neural network modules.
sync_dataset.py
Implements the synthetic dataset classes described in the paper. This includes various data generation methods and dataset wrappers for training and evaluation.
Other Python Files
All other .py files are runnable scripts. Their filenames follow the pattern:
```
dataset_modelmethod.py
```
where dataset specifies the dataset used, and modelmethod specifies the model or method applied. For example, activation_sae.py runs the Sparse Autoencoder (SAE) on the activation dataset.

To run an experiment, execute the corresponding Python script.
For example:

python activation_sae.py

For more details on the datasets and models, please refer to the comments in models.py and sync_dataset.py.

Name		Name	Last commit message	Last commit date
Latest commit History 2 Commits
README.md		README.md
activation_sae.py		activation_sae.py
activation_sae_log.py		activation_sae_log.py
activation_sae_topk.py		activation_sae_topk.py
activation_vae.py		activation_vae.py
activation_vaep.py		activation_vaep.py
embedding_sae.py		embedding_sae.py
embedding_sae_log.py		embedding_sae_log.py
embedding_sae_topk.py		embedding_sae_topk.py
embedding_vae.py		embedding_vae.py
embedding_vaep.py		embedding_vaep.py
fmnist_vaep.py		fmnist_vaep.py
interactivation_AD-RE.png		interactivation_AD-RE.png
models.py		models.py
sync_dataset.py		sync_dataset.py
sync_vaep_linear.py		sync_vaep_linear.py
test.ipynb		test.ipynb
utils.py		utils.py