Alternatives and similar repositories for automated-interpretability

Users that are interested in automated-interpretability are comparing it to the libraries listed below

• hijohnnylin / neuronpedia-scorer
  ☆17Updated last year
• callummcdougall / sae-exercises-mats
  ☆22Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆52Updated last month
• 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…
  ☆26Updated last year
• KoyenaPal / future-lens
  Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
  ☆18Updated last year
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆55Updated 7 months ago
• ckkissane / sae-transfer
  Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"
  ☆11Updated 10 months ago
• aaronmueller / MIB
  Landing page for MIB: A Mechanistic Interpretability Benchmark
  ☆10Updated last week
• callummcdougall / sae_visualizer
  ☆28Updated last year
• jbloomAus / SAEDashboard
  ☆50Updated last month
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆65Updated last month
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆89Updated last week
• koayon / atp_star
  PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)
  ☆18Updated 4 months ago
• tilde-research / activault
  Engine for collecting, uploading, and downloading model activations
  ☆18Updated 2 months ago
• adamkarvonen / SAE_BoardGameEval
  ☆23Updated 4 months ago
• Butanium / nnterp
  A small package implementing some useful wrapping around nnsight
  ☆13Updated last month
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆75Updated 6 months ago
• 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 11 months ago
• Jiaxin-Wen / MisleadLM
  Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""
  ☆14Updated 7 months ago
• saprmarks / geometry-of-truth
  ☆83Updated 9 months ago
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆65Updated last year
• tilde-research / sieve
  Applying SAEs for fine-grained control
  ☆18Updated 5 months ago
• samuelarnesen / nyu-debate-modeling
  ☆21Updated 8 months ago
• r-three / RAD
  Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model
  ☆43Updated last year
• amack315 / unsupervised-steering-vectors
  ☆31Updated last year
• ApolloResearch / apd
  Attribution-based Parameter Decomposition
  ☆23Updated this week
• scottlogic-alex / prm800k-denorm
  Script for processing OpenAI's PRM800K process supervision dataset into an Alpaca-style instruction-response format
  ☆27Updated last year
• casmlab / NPHardEval
  Repository for NPHardEval, a quantified-dynamic benchmark of LLMs
  ☆54Updated last year
• AsaCooperStickland / situational-awareness-evals
  Measuring the situational awareness of language models
  ☆35Updated last year
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆20Updated 6 months ago