Alternatives and similar repositories for dictionary_learning_demo

Users that are interested in dictionary_learning_demo are comparing it to the libraries listed below

• adamkarvonen / SAEBench
  ☆105Updated last month
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆49Updated 9 months ago
• KihoPark / linear_rep_geometry
  ☆99Updated 5 months ago
• MaheepChaudhary / SAE-Ravel
  Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…
  ☆11Updated 5 months ago
• IBM / activation-steering
  General-purpose activation steering library
  ☆83Updated 2 months ago
• roeehendel / icl_task_vectors
  ☆95Updated last year
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆74Updated 4 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆70Updated 2 months ago
• hannamw / EAP-IG
  ☆40Updated last month
• javiferran / sae_entities
  ☆51Updated 4 months ago
• wesg52 / sparse-probing-paper
  Sparse probing paper full code.
  ☆58Updated last year
• saprmarks / feature-circuits
  ☆182Updated 3 months ago
• ykwon0407 / DataInf
  DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)
  ☆71Updated 9 months ago
• bartbussmann / matryoshka_sae
  ☆35Updated 5 months ago
• balevinstein / Probes
  ☆51Updated 2 years ago
• ericwtodd / function_vectors
  Function Vectors in Large Language Models (ICLR 2024)
  ☆170Updated 2 months ago
• saprmarks / geometry-of-truth
  ☆87Updated 11 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆40Updated last year
• jacobdunefsky / transcoder_circuits
  ☆140Updated 7 months ago
• logix-project / logix
  AI Logging for Interpretability and Explainability🔬
  ☆124Updated last year
• TRAIS-Lab / dattri
  `dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.
  ☆78Updated last month
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆162Updated last year
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆65Updated last year
• redwoodresearch / Easy-Transformer
  ☆121Updated 11 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆231Updated 9 months ago
• dannyallover / overthinking_the_truth
  ☆29Updated last year
• yuzhaouoe / SAE-based-representation-engineering
  [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
  ☆60Updated 7 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆95Updated last year
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆192Updated last week
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆53Updated 2 months ago