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.
  ☆181Updated 6 months ago
• ethancaballero / broken_neural_scaling_laws
  Code Release for "Broken Neural Scaling Laws" (BNSL) paper
  ☆59Updated 2 years ago
• bilal-chughtai / rep-theory-mech-interp
  ☆28Updated 2 years ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆132Updated 3 years ago
• mechanistic-interpretability-grokking / progress-measures-paper
  ☆73Updated 3 years ago
• Sea-Snell / grokking
  unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
  ☆81Updated 3 years ago
• epfml / llm-baselines
  nanoGPT-like codebase for LLM training
  ☆114Updated 2 months ago
• edwardjhu / TP4
  Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)
  ☆63Updated 4 years ago
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆136Updated last year
• EleutherAI / features-across-time
  Understanding how features learned by neural networks evolve throughout training
  ☆41Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆56Updated 8 months ago
• wesg52 / universal-neurons
  Universal Neurons in GPT2 Language Models
  ☆31Updated last year
• princeton-nlp / TransformerPrograms
  [NeurIPS 2023] Learning Transformer Programs
  ☆162Updated last year
• shikaiqiu / compute-better-spent
  ☆62Updated 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
• adamkarvonen / SAE_BoardGameEval
  ☆23Updated 11 months ago
• srush / do-we-need-attention
  ☆167Updated 2 years ago
• KhoomeiK / complexity-scaling
  gzip Predicts Data-dependent Scaling Laws
  ☆34Updated last year
• taufeeque9 / codebook-features
  Sparse and discrete interpretability tool for neural networks
  ☆65Updated last year
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆132Updated 2 years ago
• abhishekpanigrahi1996 / transformer_in_transformer
  ☆45Updated 2 years ago
• AllanYangZhou / universal_neural_functional
  ☆54Updated last year
• cloneofsimo / min-fsdp
  ☆92Updated last year
• vvvm23 / mamba-jax
  Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX
  ☆92Updated last year
• berlino / seq_icl
  ☆53Updated last year
• lucidrains / pause-transformer
  Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…
  ☆53Updated 2 years ago
• yixiaoer / mistral-v0.2-jax
  JAX implementation of the Mistral 7b v0.2 model
  ☆35Updated last year
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆14Updated 3 years ago
• bhoov / energy-transformer-jax
  The Energy Transformer block, in JAX
  ☆63Updated 2 years ago
• Silent-Zebra / twisted-smc-lm
  ☆31Updated 9 months ago