Alternatives and similar repositories for Sparse-Autoencoder

Users that are interested in Sparse-Autoencoder are comparing it to the libraries listed below

• taufeeque9 / codebook-features
  Sparse and discrete interpretability tool for neural networks
  ☆63Updated last year
• 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…
  ☆27Updated last year
• callummcdougall / sae-exercises-mats
  ☆22Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆52Updated last month
• bhaweshiitk / ConformalLLM
  Extending Conformal Prediction to LLMs
  ☆67Updated last year
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆95Updated 3 weeks ago
• snu-mllab / Targeted-Cause-Discovery
  Official implementation for "Targeted Cause Discovery with Data-Driven Learning"
  ☆23Updated 9 months ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆75Updated 7 months ago
• epfml / DenseFormer
  ☆81Updated last year
• apple / ml-entity-deduction-arena
  ☆32Updated last year
• Bradley-Butcher / Conformers
  Unofficial implementation of Conformal Language Modeling by Quach et al
  ☆28Updated last year
• LoryPack / LLM-LieDetector
  Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"
  ☆70Updated last year
• bartbussmann / BatchTopK
  Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)
  ☆42Updated last month
• jonhue / activeft
  PyTorch library for Active Fine-Tuning
  ☆80Updated 4 months ago
• UW-Madison-Lee-Lab / LanguageInterfacedFineTuning
  Code for Language-Interfaced FineTuning for Non-Language Machine Learning Tasks.
  ☆128Updated 7 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆202Updated 6 months ago
• peterljq / Parsimonious-Concept-Engineering
  PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)
  ☆37Updated 7 months ago
• multimodal-interpretability / maia
  Official implementation of MAIA, A Multimodal Automated Interpretability Agent
  ☆82Updated last week
• callummcdougall / sae_visualizer
  ☆28Updated last year
• adamkarvonen / SAEBench
  ☆101Updated 3 weeks ago
• allenai / infinigram-api
  ☆61Updated 3 weeks ago
• ExtensityAI / benchmark
  Evaluation of neuro-symbolic engines
  ☆36Updated 10 months ago
• shuoli90 / Rank-Calibration
  This is the repo for constructing a comprehensive and rigorous evaluation framework for LLM calibration.
  ☆13Updated last year
• wesg52 / universal-neurons
  Universal Neurons in GPT2 Language Models
  ☆29Updated last year
• KihoPark / linear_rep_geometry
  ☆95Updated 4 months ago
• vinid / NegotiationArena
  ☆69Updated last year
• facebookresearch / ModelRatatouille
  Recycling diverse models
  ☆44Updated 2 years ago
• apple / ml-planner
  ☆53Updated last year
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆108Updated last year
• AsaCooperStickland / situational-awareness-evals
  Measuring the situational awareness of language models
  ☆35Updated last year