Alternatives and similar repositories for superposition

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

• bilal-chughtai / rep-theory-mech-interp
  ☆26Updated 2 years ago
• vvvm23 / mamba-jax
  Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX
  ☆81Updated last year
• abhishekpanigrahi1996 / transformer_in_transformer
  ☆45Updated last year
• dvruette / barrel-rec-pytorch
  ☆53Updated last year
• bhoov / energy-transformer-jax
  The Energy Transformer block, in JAX
  ☆56Updated last year
• young-geng / mintext
  Minimal but scalable implementation of large language models in JAX
  ☆34Updated 7 months ago
• callummcdougall / sae_visualizer
  ☆27Updated last year
• srush / mamba-primer
  ☆37Updated last year
• EleutherAI / rnngineering
  Engineering the state of RNN language models (Mamba, RWKV, etc.)
  ☆32Updated last year
• srush / anynp
  Proof-of-concept of global switching between numpy/jax/pytorch in a library.
  ☆18Updated 11 months ago
• Silent-Zebra / twisted-smc-lm
  ☆29Updated 2 months ago
• dylandoblar / noether-networks
  Meta-learning inductive biases in the form of useful conserved quantities.
  ☆37Updated 2 years ago
• srush / triton-autodiff
  Experiment of using Tangent to autodiff triton
  ☆78Updated last year
• cloneofsimo / min-fsdp
  ☆78Updated 10 months ago
• Sea-Snell / grokking
  unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
  ☆78Updated 2 years ago
• radarFudan / mamba-minimal-jax
  ☆28Updated 6 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆50Updated last month
• ClashLuke / tpucare
  Automatically take good care of your preemptible TPUs
  ☆36Updated 2 years ago
• taufeeque9 / codebook-features
  Sparse and discrete interpretability tool for neural networks
  ☆63Updated last year
• ethancaballero / broken_neural_scaling_laws
  Code Release for "Broken Neural Scaling Laws" (BNSL) paper
  ☆58Updated last year
• aks2203 / easy-to-hard
  Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"
  ☆59Updated 3 years ago
• irregular-rhomboid / EAI-Math-Reading-Group
  Resources from the EleutherAI Math Reading Group
  ☆53Updated 3 months ago
• EleutherAI / features-across-time
  Understanding how features learned by neural networks evolve throughout training
  ☆34Updated 7 months ago
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆73Updated 7 months ago
• yixiaoer / einshard
  Einsum-like high-level array sharding API for JAX
  ☆34Updated 10 months ago
• young-geng / mlxu
  Machine Learning eXperiment Utilities
  ☆46Updated 11 months ago
• danielmamay / grokking
  Implementation of OpenAI's 'Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets' paper.
  ☆36Updated last year
• yixiaoer / mistral-v0.2-jax
  JAX implementation of the Mistral 7b v0.2 model
  ☆34Updated 10 months ago
• mlfoundations / scaling
  Language models scale reliably with over-training and on downstream tasks
  ☆97Updated last year
• wesg52 / universal-neurons
  Universal Neurons in GPT2 Language Models
  ☆29Updated last year