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 last year
• EleutherAI / rnngineering
  Engineering the state of RNN language models (Mamba, RWKV, etc.)
  ☆32Updated 8 months ago
• taufeeque9 / codebook-features
  Sparse and discrete interpretability tool for neural networks
  ☆59Updated 11 months ago
• EleutherAI / mdl
  Minimum Description Length probing for neural network representations
  ☆18Updated this week
• AllanYangZhou / universal_neural_functional
  ☆48Updated 11 months ago
• ethancaballero / broken_neural_scaling_laws
  Code Release for "Broken Neural Scaling Laws" (BNSL) paper
  ☆57Updated last year
• bhoov / energy-transformer-jax
  The Energy Transformer block, in JAX
  ☆54Updated 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"
  ☆60Updated 2 years ago
• srush / anynp
  Proof-of-concept of global switching between numpy/jax/pytorch in a library.
  ☆18Updated 7 months ago
• EleutherAI / features-across-time
  Understanding how features learned by neural networks evolve throughout training
  ☆32Updated 3 months ago
• srush / mamba-primer
  ☆37Updated 9 months ago
• AsaCooperStickland / situational-awareness-evals
  Measuring the situational awareness of language models
  ☆33Updated 11 months ago
• abhishekpanigrahi1996 / transformer_in_transformer
  ☆44Updated last year
• young-geng / mintext
  Minimal but scalable implementation of large language models in JAX
  ☆28Updated 2 months ago
• facebookresearch / oni
  Learn online intrinsic rewards from LLM feedback
  ☆34Updated last month
• likenneth / q_probe
  Q-Probe: A Lightweight Approach to Reward Maximization for Language Models
  ☆40Updated 7 months ago
• vvvm23 / mamba-jax
  Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX
  ☆82Updated last year
• ExtensityAI / benchmark
  Evaluation of neuro-symbolic engines
  ☆34Updated 5 months ago
• jacobdunefsky / transcoder_circuits
  ☆54Updated 2 months ago
• CerebrasResearch / Sparse-IFT
  Official repository of Sparse ISO-FLOP Transformations for Maximizing Training Efficiency
  ☆25Updated 5 months ago
• dvruette / barrel-rec-pytorch
  ☆53Updated last year
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆65Updated last year
• andyljones / boardlaw
  Scaling scaling laws with board games.
  ☆45Updated last year
• ssokota / mec
  Code for minimum-entropy coupling.
  ☆31Updated 7 months ago
• lucaslingle / mu_transformer
  Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.
  ☆30Updated last month
• mechanistic-interpretability-grokking / progress-measures-paper
  ☆59Updated 2 years ago
• ethz-spylab / superhuman-ai-consistency
  ☆28Updated last year
• berlino / seq_icl
  ☆51Updated 8 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆39Updated 3 months ago
• aks2203 / deep-thinking
  A centralized place for deep thinking code and experiments
  ☆79Updated last year