Tools for understanding how transformer predictions are built layer-by-layer
☆574Aug 7, 2025Updated 7 months ago
Alternatives and similar repositories for tuned-lens
Users that are interested in tuned-lens are comparing it to the libraries listed below
Sorting:
- A library for mechanistic interpretability of GPT-style language models☆3,183Mar 13, 2026Updated last week
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆20Oct 24, 2025Updated 4 months ago
- ☆278Oct 1, 2024Updated last year
- Interpretating the latent space representations of attention head outputs for LLMs☆39Aug 13, 2024Updated last year
- Using sparse coding to find distributed representations used by neural networks.☆298Nov 10, 2023Updated 2 years ago
- Mechanistic Interpretability Visualizations using React☆331Dec 18, 2024Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆103Sep 21, 2023Updated 2 years ago
- ☆210Oct 14, 2025Updated 5 months ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆80Mar 11, 2024Updated 2 years ago
- Training Sparse Autoencoders on Language Models☆1,261Mar 14, 2026Updated last week
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆863Updated this week
- Sparse probing paper full code.☆67Dec 17, 2023Updated 2 years ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆251Feb 27, 2026Updated 3 weeks ago
- ☆283Mar 2, 2024Updated 2 years ago
- Erasing concepts from neural representations with provable guarantees☆245Jan 27, 2025Updated last year
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆217Updated this week
- ☆1,073Mar 6, 2024Updated 2 years ago
- ☆158Dec 30, 2025Updated 2 months ago
- Sparsify transformers with SAEs and transcoders☆701Updated this week
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆868Mar 6, 2026Updated 2 weeks ago
- Sparse Autoencoder for Mechanistic Interpretability☆294Jul 20, 2024Updated last year
- Mechanistic Interpretability for Transformer Models☆53Jun 1, 2022Updated 3 years ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆175Mar 12, 2026Updated last week
- ☆403Aug 21, 2025Updated 7 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- ☆68May 18, 2023Updated 2 years ago
- ☆58Jun 15, 2023Updated 2 years ago
- Steering Llama 2 with Contrastive Activation Addition☆214May 23, 2024Updated last year
- Improving Alignment and Robustness with Circuit Breakers☆258Sep 24, 2024Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆63Oct 27, 2024Updated last year
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆361Jun 13, 2025Updated 9 months ago
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆573Jan 28, 2025Updated last year
- 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
- Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification☆11Aug 12, 2023Updated 2 years ago
- Representation Engineering: A Top-Down Approach to AI Transparency☆965Aug 14, 2024Updated last year
- The hub for EleutherAI's work on interpretability and learning dynamics☆2,745Nov 15, 2025Updated 4 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆245Updated this week
- ☆104Aug 8, 2024Updated last year
- A benchmark for mechanistic discovery of circuits in Transformers☆16Dec 15, 2024Updated last year