Sohl-Dickstein / fractal
The boundary of neural network trainability is fractal
☆195Updated last year
Alternatives and similar repositories for fractal:
Users that are interested in fractal are comparing it to the libraries listed below
- ViT Prisma is a mechanistic interpretability library for Vision Transformers (ViTs).☆213Updated this week
- ☆149Updated 6 months ago
- Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.☆165Updated last year
- Minimal GPT (~350 lines with a simple task to test it)☆62Updated 3 months ago
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆216Updated last week
- 🧠 Starter templates for doing interpretability research☆66Updated last year
- Visualizations of the theory behind diffusion models.☆135Updated 10 months ago
- Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"☆547Updated 8 months ago
- ☆164Updated 3 months ago
- 🧱 Modula software package☆169Updated this week
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆67Updated 3 months ago
- σ-GPT: A New Approach to Autoregressive Models☆61Updated 6 months ago
- For optimization algorithm research and development.☆498Updated 2 weeks ago
- Compositional Linear Algebra☆464Updated last month
- $100K or 100 Days: Trade-offs when Pre-Training with Academic Resources☆133Updated this week
- Official Implementation of the ICML 2023 paper: "Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally …☆70Updated last year
- Uncertainty quantification with PyTorch☆344Updated last week
- ☆418Updated 4 months ago
- ☆36Updated 3 months ago
- ☆212Updated 7 months ago
- The history files when recording human interaction while solving ARC tasks☆97Updated this week
- Tools for studying developmental interpretability in neural networks.☆86Updated last month
- Resources from the EleutherAI Math Reading Group☆53Updated last week
- A package for defining deep learning models using categorical algebraic expressions.☆60Updated 7 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆184Updated 2 months ago
- Interactive textbook on state-space models☆184Updated last year
- supporting pytorch FSDP for optimizers☆79Updated 3 months ago
- A simple implimentation of Bayesian Flow Networks (BFN)☆240Updated last year