wesg52 / universal-neurons

Related projects: ⓘ

• berlino / seq_icl
  ☆48Updated 3 months ago
• EleutherAI / sae-auto-interp
  ☆54Updated last week
• jacobdunefsky / transcoder_circuits
  ☆33Updated 3 months ago
• saprmarks / feature-circuits
  ☆75Updated this week
• KihoPark / linear_rep_geometry
  ☆68Updated 7 months ago
• epfml / schedules-and-scaling
  ☆47Updated 3 months ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆57Updated last week
• abhishekpanigrahi1996 / transformer_in_transformer
  ☆44Updated 11 months ago
• bilal-chughtai / rep-theory-mech-interp
  ☆23Updated last year
• KoyenaPal / future-lens
  Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
  ☆14Updated 8 months ago
• epfml / llm-baselines
  ☆68Updated 3 weeks ago
• EleutherAI / elk-generalization
  Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…
  ☆23Updated 3 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆18Updated 3 weeks ago
• taufeeque9 / codebook-features
  Sparse and discrete interpretability tool for neural networks
  ☆51Updated 7 months ago
• shikaiqiu / compute-better-spent
  ☆42Updated 3 months ago
• AllanYangZhou / universal_neural_functional
  ☆46Updated 7 months ago
• saprmarks / geometry-of-truth
  ☆64Updated last month
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆18Updated last month
• callummcdougall / sae-exercises-mats
  ☆12Updated 8 months ago
• ethancaballero / broken_neural_scaling_laws
  Code Release for "Broken Neural Scaling Laws" (BNSL) paper
  ☆57Updated 10 months ago
• KihoPark / LLM_Categorical_Hierarchical_Representations
  ☆66Updated last month
• RobertCsordas / moeut
  ☆50Updated last month
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆54Updated 10 months ago
• Ping-C / optimizer
  This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…
  ☆34Updated last year
• mlepori1 / NeuroSurgeon
  NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers
  ☆33Updated last month
• ExtensityAI / benchmark
  Evaluation of neuro-symbolic engines
  ☆29Updated last month
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆84Updated 4 months ago
• wesg52 / sparse-probing-paper
  Sparse probing paper full code.
  ☆47Updated 9 months ago
• sustcsonglin / mamba-triton
  ☆42Updated 7 months ago
• milesaturpin / cot-unfaithfulness
  ☆29Updated 10 months ago