Alternatives and similar repositories for concept-erasure:

Users that are interested in concept-erasure are comparing it to the libraries listed below

• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆192Updated 3 months ago
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆197Updated last week
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆235Updated 3 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆214Updated 6 months ago
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆165Updated last week
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆91Updated last month
• callummcdougall / sae_visualizer
  ☆26Updated 11 months ago
• justinchiu / openlogprobs
  Extract full next-token probabilities via language model APIs
  ☆237Updated last year
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆62Updated last month
• jacobdunefsky / transcoder_circuits
  ☆66Updated 4 months ago
• KihoPark / LLM_Categorical_Hierarchical_Representations
  ☆89Updated last month
• google-deepmind / mishax
  ☆124Updated last week
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆121Updated last year
• collin-burns / discovering_latent_knowledge
  ☆263Updated last year
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆481Updated 10 months ago
• adamkarvonen / SAEBench
  ☆80Updated this week
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆187Updated 10 months ago
• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆50Updated 2 years ago
• likenneth / othello_world
  Emergent world representations: Exploring a sequence model trained on a synthetic task
  ☆178Updated last year
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆170Updated 4 months ago
• EleutherAI / sparsify
  Sparsify transformers with SAEs and transcoders
  ☆499Updated this week
• nostalgebraist / transformer-utils
  Utilities for the HuggingFace transformers library
  ☆67Updated 2 years ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆134Updated 10 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆30Updated 10 months ago
• KihoPark / linear_rep_geometry
  ☆90Updated last month
• KoyenaPal / future-lens
  Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
  ☆18Updated last year
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆103Updated 4 months ago
• redwoodresearch / Easy-Transformer
  ☆114Updated 7 months ago
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆63Updated last year
• meg-tong / sycophancy-eval
  datasets from the paper "Towards Understanding Sycophancy in Language Models"
  ☆73Updated last year