Tools for understanding how transformer predictions are built layer-by-layer
☆594Aug 7, 2025Updated 10 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:
- A library for mechanistic interpretability of GPT-style language models☆3,526Updated this week
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆21Oct 24, 2025Updated 7 months ago
- ☆289Oct 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
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Mechanistic Interpretability Visualizations using React☆351Apr 30, 2026Updated last month
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆103Sep 21, 2023Updated 2 years ago
- ☆217Oct 14, 2025Updated 7 months ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆83Mar 11, 2024Updated 2 years ago
- Training Sparse Autoencoders on Language Models☆1,414Updated this week
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆948Jun 2, 2026Updated last week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆261Feb 27, 2026Updated 3 months ago
- Sparse probing paper full code.☆68Dec 17, 2023Updated 2 years ago
- ☆284Mar 2, 2024Updated 2 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Erasing concepts from neural representations with provable guarantees☆254Jan 27, 2025Updated last year
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆220Jun 1, 2026Updated last week
- ☆1,081Mar 6, 2024Updated 2 years ago
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆883Mar 6, 2026Updated 3 months ago
- Sparsify transformers with SAEs and transcoders☆725Updated this week
- ☆168May 1, 2026Updated last month
- ☆419Aug 21, 2025Updated 9 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆302Jul 20, 2024Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆195Mar 12, 2026Updated 2 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Mechanistic Interpretability for Transformer Models☆53Jun 1, 2022Updated 4 years ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- ☆67May 18, 2023Updated 3 years ago
- ☆58Jun 15, 2023Updated 2 years ago
- Steering Llama 2 with Contrastive Activation Addition☆234May 23, 2024Updated 2 years ago
- Improving Alignment and Robustness with Circuit Breakers☆262Sep 24, 2024Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆67Oct 27, 2024Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆72Jun 19, 2024Updated last year
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆582Jan 28, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification☆11Aug 12, 2023Updated 2 years ago
- The hub for EleutherAI's work on interpretability and learning dynamics☆2,814Nov 15, 2025Updated 6 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆402Jun 13, 2025Updated 11 months ago
- Representation Engineering: A Top-Down Approach to AI Transparency☆1,004Aug 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…☆101Sep 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 …☆258Jun 1, 2026Updated last week
- A benchmark for mechanistic discovery of circuits in Transformers☆17Dec 15, 2024Updated last year