Alternatives and similar repositories for interpretability

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

• nostalgebraist / transformer-utils
  Utilities for the HuggingFace transformers library
  ☆72Updated 2 years ago
• interpretingdl / eacl2024_transformer_interpretability_tutorial
  Materials for EACL2024 tutorial: Transformer-specific Interpretability
  ☆61Updated last year
• ArthurConmy / Automatic-Circuit-Discovery
  ☆260Updated last year
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆303Updated last year
• aaronmueller / MIB
  Landing page for MIB: A Mechanistic Interpretability Benchmark
  ☆22Updated 4 months ago
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆57Updated last month
• mega002 / lm-debugger
  The official code of LM-Debugger, an interactive tool for inspection and intervention in transformer-based language models.
  ☆180Updated 3 years ago
• KihoPark / LLM_Categorical_Hierarchical_Representations
  ☆112Updated 10 months ago
• aryamanarora / causalgym
  CausalGym: Benchmarking causal interpretability methods on linguistic tasks
  ☆51Updated last year
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆134Updated 10 months ago
• adamkarvonen / SAEBench
  ☆136Updated last month
• redwoodresearch / Easy-Transformer
  ☆134Updated last year
• jacobdunefsky / transcoder_circuits
  ☆192Updated last year
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆132Updated 2 years ago
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆554Updated 4 months ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆201Updated last year
• inseq-team / inseq
  Interpretability for sequence generation models 🐛 🔍
  ☆450Updated 2 weeks ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆100Updated 2 years ago
• hendrycks / ethics
  Aligning AI With Shared Human Values (ICLR 2021)
  ☆306Updated 2 years ago
• PAIR-code / pretraining-tda
  ☆32Updated 10 months ago
• HannahKirk / prism-alignment
  The Prism Alignment Project
  ☆87Updated 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 …
  ☆234Updated last week
• mlepori1 / NeuroSurgeon
  NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers
  ☆42Updated 10 months ago
• collin-burns / discovering_latent_knowledge
  ☆283Updated last year
• evandez / REMEDI
  Inspecting and Editing Knowledge Representations in Language Models
  ☆119Updated 2 years ago
• davidbau / baukit
  ☆240Updated last year
• fdalvi / NeuroX
  A Python library that encapsulates various methods for neuron interpretation and analysis in Deep NLP models.
  ☆105Updated 2 years ago
• tatsu-lab / opinions_qa
  ☆116Updated last year
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆232Updated last year
• ARBORproject / arborproject.github.io
  ☆83Updated 9 months ago