Erasing concepts from neural representations with provable guarantees
☆245Jan 27, 2025Updated last year
Alternatives and similar repositories for concept-erasure
Users that are interested in concept-erasure are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆36Jul 14, 2022Updated 3 years ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆217Mar 16, 2026Updated last week
- ☆12Oct 23, 2022Updated 3 years ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28May 23, 2024Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆576Aug 7, 2025Updated 7 months ago
- Algebraic value editing in pretrained language models☆69Nov 1, 2023Updated 2 years ago
- Understanding how features learned by neural networks evolve throughout training☆41Oct 24, 2024Updated last year
- ☆282Mar 2, 2024Updated 2 years ago
- ☆52Oct 23, 2023Updated 2 years ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆245Mar 16, 2026Updated last week
- ☆157Dec 30, 2025Updated 2 months ago
- Mechanistic Interpretability Visualizations using React☆331Dec 18, 2024Updated last year
- A library for mechanistic interpretability of GPT-style language models☆3,223Updated this week
- ☆91Jun 6, 2022Updated 3 years ago
- ☆30Aug 2, 2024Updated last year
- ☆58Jun 15, 2023Updated 2 years ago
- ☆19Mar 5, 2024Updated 2 years ago
- suffix array construction and searching algorithms for in-memory binary data.☆12Sep 10, 2022Updated 3 years ago
- ☆278Oct 1, 2024Updated last year
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated last year
- ☆558Feb 5, 2024Updated 2 years ago
- ☆119Feb 11, 2025Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- A TinyStories LM with SAEs and transcoders☆14Apr 3, 2025Updated 11 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆27Nov 20, 2024Updated last year
- ☆44Nov 17, 2024Updated last year
- Mass-editing thousands of facts into a transformer memory (ICLR 2023)☆544Jan 31, 2024Updated 2 years ago
- Sparsify transformers with SAEs and transcoders☆701Mar 16, 2026Updated last week
- ☆104Aug 8, 2024Updated last year
- Sparse Autoencoder Training Library☆55May 1, 2025Updated 10 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆863Updated this week
- Function Vectors in Large Language Models (ICLR 2024)☆193Apr 17, 2025Updated 11 months ago
- Representation Engineering: A Top-Down Approach to AI Transparency☆965Aug 14, 2024Updated last year
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆868Mar 6, 2026Updated 2 weeks ago
- ☆147Jul 23, 2025Updated 8 months ago
- ☆48Feb 8, 2025Updated last year
- Fast, Modern, and Low Precision PyTorch Optimizers☆128Dec 29, 2025Updated 2 months ago
- Locating and editing factual associations in GPT (NeurIPS 2022)☆736Apr 20, 2024Updated last year
- ☆60Mar 9, 2023Updated 3 years ago