Alternatives and similar repositories for superposition:

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

• srush / anynp
  Proof-of-concept of global switching between numpy/jax/pytorch in a library.
  ☆18Updated 7 months ago
• ethancaballero / broken_neural_scaling_laws
  Code Release for "Broken Neural Scaling Laws" (BNSL) paper
  ☆58Updated last year
• EleutherAI / features-across-time
  Understanding how features learned by neural networks evolve throughout training
  ☆32Updated 3 months ago
• bilal-chughtai / rep-theory-mech-interp
  ☆26Updated last year
• dylandoblar / noether-networks
  Meta-learning inductive biases in the form of useful conserved quantities.
  ☆37Updated 2 years ago
• bhoov / energy-transformer-jax
  The Energy Transformer block, in JAX
  ☆55Updated last year
• EleutherAI / rnngineering
  Engineering the state of RNN language models (Mamba, RWKV, etc.)
  ☆32Updated 8 months ago
• aks2203 / easy-to-hard
  Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"
  ☆60Updated 2 years ago
• dvruette / barrel-rec-pytorch
  ☆53Updated last year
• ExtensityAI / benchmark
  Evaluation of neuro-symbolic engines
  ☆34Updated 6 months ago
• young-geng / mintext
  Minimal but scalable implementation of large language models in JAX
  ☆31Updated 3 months ago
• AsaCooperStickland / situational-awareness-evals
  Measuring the situational awareness of language models
  ☆34Updated last year
• Silent-Zebra / twisted-smc-lm
  ☆24Updated this week
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆70Updated 3 months ago
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆94Updated 2 months ago
• AllanYangZhou / universal_neural_functional
  ☆49Updated last year
• edwardjhu / TP4
  Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)
  ☆59Updated 3 years ago
• GallagherCommaJack / modulax
  ☆15Updated 5 months ago
• jenkspt / gpt-jax
  Jax/Flax rewrite of Karpathy's nanoGPT
  ☆55Updated 2 years ago
• taufeeque9 / codebook-features
  Sparse and discrete interpretability tool for neural networks
  ☆58Updated last year
• DAIOS-AI / mindscript
  A programming language for formal/informal computation.
  ☆41Updated this week
• HomebrewML / HomebrewNLP-torch
  A case study of efficient training of large language models using commodity hardware.
  ☆68Updated 2 years ago
• lucaslingle / mu_transformer
  Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.
  ☆30Updated 2 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆36Updated 3 months ago
• KhoomeiK / complexity-scaling
  gzip Predicts Data-dependent Scaling Laws
  ☆34Updated 8 months ago
• vvvm23 / mamba-jax
  Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX
  ☆82Updated last year
• lucidrains / esbn-transformer
  An attempt to merge ESBN with Transformers, to endow Transformers with the ability to emergently bind symbols
  ☆15Updated 3 years ago
• AndPotap / einsum-search
  ☆29Updated 4 months ago
• microsoft / mechanistic-error-probe
  A mechanistic approach for understanding and detecting factual errors of large language models.
  ☆40Updated 7 months ago
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆102Updated last month