Erasing concepts from neural representations with provable guarantees
☆243Jan 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
Sorting:
- ☆36Jul 14, 2022Updated 3 years ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆217Feb 23, 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☆567Aug 7, 2025Updated 6 months ago
- Algebraic value editing in pretrained language models☆68Nov 1, 2023Updated 2 years ago
- ☆284Mar 2, 2024Updated 2 years ago
- Understanding how features learned by neural networks evolve throughout training☆41Oct 24, 2024Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆243Feb 23, 2026Updated last week
- ☆153Dec 30, 2025Updated 2 months ago
- ☆273Oct 1, 2024Updated last year
- Mechanistic Interpretability Visualizations using React☆326Dec 18, 2024Updated last year
- ☆19Mar 5, 2024Updated last year
- Minimum Description Length probing for neural network representations☆20Jan 28, 2025Updated last year
- ☆552Feb 5, 2024Updated 2 years ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- A library for mechanistic interpretability of GPT-style language models☆3,133Updated this week
- ☆52Oct 23, 2023Updated 2 years ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated last year
- Mass-editing thousands of facts into a transformer memory (ICLR 2023)☆541Jan 31, 2024Updated 2 years ago
- ☆44Nov 17, 2024Updated last year
- A library for efficient patching and automatic circuit discovery.☆90Dec 31, 2025Updated 2 months ago
- ☆57Jun 15, 2023Updated 2 years ago
- ☆117Feb 11, 2025Updated last year
- ☆147Jul 23, 2025Updated 7 months ago
- ☆90Jun 6, 2022Updated 3 years ago
- Representation Engineering: A Top-Down Approach to AI Transparency☆953Aug 14, 2024Updated last year
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆863Jan 29, 2026Updated last month
- A TinyStories LM with SAEs and transcoders☆14Apr 3, 2025Updated 11 months ago
- A benchmark for mechanistic discovery of circuits in Transformers☆16Dec 15, 2024Updated last year
- ☆30Aug 2, 2024Updated last year
- Training Sparse Autoencoders on Language Models☆1,233Updated this week
- Sparsify transformers with SAEs and transcoders☆696Feb 23, 2026Updated last week
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆27Nov 20, 2024Updated last year
- ☆66Feb 16, 2023Updated 3 years ago
- Function Vectors in Large Language Models (ICLR 2024)☆192Apr 17, 2025Updated 10 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆825Feb 23, 2026Updated last week
- This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…☆25Feb 16, 2026Updated 2 weeks ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆71Jun 19, 2024Updated last year