HugoFry / mats_sae_training_for_ViTs

Related projects ⓘ

Alternatives and complementary repositories for mats_sae_training_for_ViTs

• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆31Updated last month
• jacobdunefsky / transcoder_circuits
  ☆44Updated this week
• understanding-search / maze-transformer
  This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.
  ☆24Updated 2 months 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…
  ☆25Updated 5 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆108Updated last year
• adamkarvonen / SAE_BoardGameEval
  ☆13Updated last month
• saprmarks / feature-circuits
  ☆105Updated last month
• jbloomAus / SAEDashboard
  ☆20Updated last week
• mishajw / repeng
  Experiments with representation engineering
  ☆10Updated 8 months ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆61Updated last week
• KihoPark / linear_rep_geometry
  ☆76Updated 9 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆26Updated 5 months ago
• EleutherAI / sae-auto-interp
  ☆107Updated this week
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆27Updated 3 weeks ago
• hannamw / EAP-IG
  ☆13Updated 2 months ago
• bilal-chughtai / rep-theory-mech-interp
  ☆26Updated last year
• mechanistic-interpretability-grokking / progress-measures-paper
  ☆54Updated 2 years ago
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆57Updated last year
• callummcdougall / sae_visualizer
  ☆24Updated 7 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆16Updated 3 weeks ago
• amack315 / unsupervised-steering-vectors
  ☆24Updated 6 months ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆98Updated 5 months ago
• saprmarks / dictionary_learning
  ☆145Updated 3 weeks ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆78Updated last year
• saprmarks / geometry-of-truth
  ☆71Updated 3 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆188Updated last month
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆84Updated 8 months ago
• redwoodresearch / Easy-Transformer
  ☆98Updated 3 months ago
• vedantpalit / Towards-Vision-Language-Mechanistic-Interpretability
  This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…
  ☆17Updated 7 months ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆97Updated 2 years ago