jettjaniak / chainscopeLinks
Repository for the "Chain-of-Thought Reasoning In The Wild Is Not Always Faithful" paper
☆31Updated last month
Alternatives and similar repositories for chainscope
Users that are interested in chainscope are comparing it to the libraries listed below
Sorting:
- A toolkit for describing model features and intervening on those features to steer behavior.☆225Updated last month
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆235Updated 2 weeks ago
- Sparse Autoencoder for Mechanistic Interpretability☆285Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆206Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆137Updated 10 months ago
- ☆193Updated last year
- Open source interpretability artefacts for R1.☆165Updated 8 months ago
- ⚓️ Repository for the "Thought Anchors: Which LLM Reasoning Steps Matter?" paper.☆104Updated 2 months ago
- ☆58Updated last year
- ☆86Updated 11 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆236Updated last year
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆327Updated 6 months ago
- Using sparse coding to find distributed representations used by neural networks.☆290Updated 2 years ago
- Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.☆168Updated this week
- This repository contains the code and data for the paper "SelfIE: Self-Interpretation of Large Language Model Embeddings" by Haozhe Chen,…☆55Updated last year
- Repository for the paper Stream of Search: Learning to Search in Language☆152Updated 11 months ago
- ☆140Updated last week
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models☆322Updated 5 months ago
- ☆383Updated 4 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆63Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆100Updated 2 years ago
- Governance of the Commons Simulation (GovSim)☆64Updated 11 months ago
- ☆83Updated 3 weeks ago
- ☆202Updated 2 months ago
- ☆239Updated last month
- ☆262Updated last year
- ☆82Updated 3 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆132Updated 3 years ago
- ☆127Updated 2 months ago
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆189Updated 10 months ago