Add requirements.txt
Update README.md
Add new global var for feature name file
Add code for generating html view of feature names and examples
Update database code to include text and token
Update .gitignore file
Move some methods around

Update gitignore file
Move activation db code to own file
Add code for actually naming a feature
Update README.md

Improve SAE stuff by making sure it is on cuda
Improve getting activations for features (setting limits)
Add first test of stored activations from database
Add more global variable (I love those) for improving naming conventions
Move models to folder to keep everything crispy clean

Add database class to store results

Improve autoencoder training
Move constants and SparseAutoencoder class to own file
Move hyperparameters to own file
Update .gitignore

Add visualization of sae feature activations for a few sample data points. Does not work properly yet

Add DataLoader class to load activations

Improve calculating activations
Scale down model and therefore compute and disk requirements
Reduce reserved memory for slurm task, as it was not needed

Add calculate_activations.py
Update .gitignore
Implement retrieving activations from model for data

Add .gitignore
Add run shell files for slurm
Implement loading and querying Phi2
Implement downloading and preprocessing data