Tools for understanding how transformer predictions are built layer-by-layer
☆604Aug 7, 2025Updated 11 months ago
Alternatives and similar repositories for tuned-lens
Users that are interested in tuned-lens are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆21Oct 24, 2025Updated 8 months ago
- A library for mechanistic interpretability of GPT-style language models☆3,695Updated this week
- ☆293Oct 1, 2024Updated last year
- Using sparse coding to find distributed representations used by neural networks.☆306Nov 10, 2023Updated 2 years ago
- Interpretating the latent space representations of attention head outputs for LLMs☆39Aug 13, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Mechanistic Interpretability Visualizations using React☆358Apr 30, 2026Updated 2 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆104Sep 21, 2023Updated 2 years ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆87Mar 11, 2024Updated 2 years ago
- ☆223Oct 14, 2025Updated 9 months ago
- Sparse probing paper full code.☆68Dec 17, 2023Updated 2 years ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆265Feb 27, 2026Updated 4 months ago
- ☆287Mar 2, 2024Updated 2 years ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆995Jul 14, 2026Updated last week
- Erasing concepts from neural representations with provable guarantees☆258Jan 27, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Training Sparse Autoencoders on Language Models☆1,476Updated this week
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆221Jul 13, 2026Updated last week
- ☆1,082Mar 6, 2024Updated 2 years ago
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆892Mar 6, 2026Updated 4 months ago
- Sparsify transformers with SAEs and transcoders☆732Updated this week
- ☆427Aug 21, 2025Updated 11 months ago
- Mechanistic Interpretability for Transformer Models☆53Jun 1, 2022Updated 4 years ago
- Sparse Autoencoder for Mechanistic Interpretability☆303Jul 20, 2024Updated 2 years ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆58Jun 15, 2023Updated 3 years ago
- ☆67May 18, 2023Updated 3 years ago
- Steering Llama 2 with Contrastive Activation Addition☆240May 23, 2024Updated 2 years ago
- Improving Alignment and Robustness with Circuit Breakers☆266Sep 24, 2024Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆68Oct 27, 2024Updated last year
- ☆177May 1, 2026Updated 2 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆74Jun 19, 2024Updated 2 years ago
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆581Jan 28, 2025Updated last year
- The hub for EleutherAI's work on interpretability and learning dynamics☆2,858Nov 15, 2025Updated 8 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification☆11Aug 12, 2023Updated 2 years ago
- Representation Engineering: A Top-Down Approach to AI Transparency☆1,012Aug 14, 2024Updated last year
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆103Sep 5, 2021Updated 4 years ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆266Jul 13, 2026Updated last week
- ☆256Feb 22, 2024Updated 2 years ago
- ☆113Aug 8, 2024Updated last year
- Locating and editing factual associations in GPT (NeurIPS 2022)☆770Apr 20, 2024Updated 2 years ago