Alternatives and similar repositories for superposition

Users that are interested in superposition are comparing it to the libraries listed below

• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆180Updated 5 months ago
• srush / do-we-need-attention
  ☆167Updated 2 years ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆131Updated 3 years ago
• Sea-Snell / grokking
  unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
  ☆81Updated 3 years ago
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆135Updated last year
• bilal-chughtai / rep-theory-mech-interp
  ☆27Updated 2 years ago
• irregular-rhomboid / EAI-Math-Reading-Group
  Resources from the EleutherAI Math Reading Group
  ☆54Updated 9 months ago
• ethancaballero / broken_neural_scaling_laws
  Code Release for "Broken Neural Scaling Laws" (BNSL) paper
  ☆59Updated 2 years ago
• berlino / seq_icl
  ☆53Updated last year
• HazyResearch / zoology
  Understand and test language model architectures on synthetic tasks.
  ☆246Updated 2 months ago
• shikaiqiu / compute-better-spent
  ☆62Updated last year
• epfml / llm-baselines
  nanoGPT-like codebase for LLM training
  ☆113Updated last month
• EleutherAI / features-across-time
  Understanding how features learned by neural networks evolve throughout training
  ☆40Updated last year
• google-deepmind / nanodo
  ☆285Updated last year
• cloneofsimo / min-fsdp
  ☆91Updated last year
• Ping-C / optimizer
  This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…
  ☆40Updated 2 years ago
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆198Updated last year
• KindXiaoming / Omnigrok
  Omnigrok: Grokking Beyond Algorithmic Data
  ☆62Updated 2 years ago
• vvvm23 / mamba-jax
  Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX
  ☆92Updated last year
• MatX-inc / seqax
  seqax = sequence modeling + JAX
  ☆169Updated 4 months ago
• princeton-nlp / TransformerPrograms
  [NeurIPS 2023] Learning Transformer Programs
  ☆162Updated last year
• mechanistic-interpretability-grokking / progress-measures-paper
  ☆70Updated 3 years ago
• taufeeque9 / codebook-features
  Sparse and discrete interpretability tool for neural networks
  ☆65Updated last year
• Silent-Zebra / twisted-smc-lm
  ☆31Updated 8 months ago
• davisyoshida / lorax
  LoRA for arbitrary JAX models and functions
  ☆143Updated last year
• google-deepmind / neural_networks_chomsky_hierarchy
  Neural Networks and the Chomsky Hierarchy
  ☆212Updated last year
• edwardjhu / TP4
  Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)
  ☆63Updated 4 years ago
• abhishekpanigrahi1996 / transformer_in_transformer
  ☆45Updated 2 years ago
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆86Updated last year
• Sea-Snell / JAXSeq
  Train very large language models in Jax.
  ☆210Updated 2 years ago