firstuserhere

generative-ai-for-beginners

18 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

x-transformers

A concise but complete full-attention transformer with a set of promising experimental features from various papers

grok

transformer-debugger

xzbot

notes, honeypot, and exploit demo for the xz backdoor (CVE-2024-3094)

lit

The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.

disentangling-vae

Experiments for understanding disentanglement in VAE latent representations

rq-vae-transformer

The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)

llm-transparency-tool

LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/llm-transparency-tool-demo

Beta-VAE

Pytorch implementation of β-VAE

ComPromptMized

ComPromptMized: Unleashing Zero-click Worms that Target GenAI-Powered Applications

sae_vis

Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).

feature-circuits

lw2-viewer

An alternative frontend for LessWrong 2.0

hugo-texify3

A LaTeX-style hugo theme with the gruvbox color scheme for personal blogging

AnyLanguage-Word-Guessing-Game

A word guessing game that can be modified and translated to your language!

everything-you-need

we got you bro

tinynarrations

A synthetic story narration dataset to study small audio LMs.

VISIT-Visualizing-Transformers

finetuning

This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking".

dine

Year-Progress-Bar

superposition-geometry-toys

Experiments for running toy models of superposition as in Anthropic's 2022 paper. These experiments focus on superposition of composed features.

saex

SAEs in Jax

MG2023

sae_alternatives

aisc_oocl_experiments

experiments trying to elicit out of context learning when training a transformer on a simple task

llm-sandbag-activation-steering

matching-pursuit

This repository contains research and experiments aimed at producing sparse, interpretable representations of audio.

Ponita_SLR

Fast, Expressive SE(n) Equivariant Networks through Weight-Sharing in Position-Orientation Space.