⚓️ Repository for the "Thought Anchors: Which LLM Reasoning Steps Matter?" paper.
☆121Oct 27, 2025Updated 6 months ago
Alternatives and similar repositories for thought-anchors
Users that are interested in thought-anchors are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆34Jul 9, 2025Updated 9 months ago
- Repository for the "Chain-of-Thought Reasoning In The Wild Is Not Always Faithful" paper☆33Mar 31, 2026Updated last month
- A Framework for Evaluating AI Agent Safety in Realistic Environments☆31Oct 2, 2025Updated 7 months ago
- A Blackjack game with GUI written in Java.☆11Nov 21, 2018Updated 7 years ago
- Restore safety in fine-tuned language models through task arithmetic☆32Mar 28, 2024Updated 2 years ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- This was designed for interp researchers who want to do research on or with interp agents to give quality of life improvements and fix …☆141Feb 8, 2026Updated 2 months ago
- Emergent Hierarchical Reasoning in LLMs/VLMs through Reinforcement Learning [ICLR26]☆64Apr 11, 2026Updated 3 weeks ago
- A library for training crosscoders☆17May 28, 2025Updated 11 months ago
- ☆281Oct 1, 2024Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆47May 31, 2024Updated last year
- Official codebase for "Analyzing the Generalization and Reliability of Steering Vectors"☆21Dec 14, 2024Updated last year
- [CVPR 2026 Main] MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation☆22Mar 26, 2026Updated last month
- A tiny easily hackable implementation of a feature dashboard.☆16Oct 21, 2025Updated 6 months ago
- Code repo for the model organisms and convergent directions of EM papers.☆63Sep 22, 2025Updated 7 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.
- Code and materials for "Weird Generalization and Inductive Backdoors"☆38Jan 11, 2026Updated 3 months ago
- ☆54Feb 19, 2025Updated last year
- [ICML 2025] Unlearning in Diffusion Models using Sparse Autoencoders☆57Oct 16, 2025Updated 6 months ago
- Source code for our paper: "ARIA: Training Language Agents with Intention-Driven Reward Aggregation".☆28Aug 9, 2025Updated 8 months ago
- ☆67Jul 14, 2025Updated 9 months ago
- James' cookbook of evaluations and finetuning experiments☆26Feb 19, 2026Updated 2 months ago
- ☆16Feb 4, 2025Updated last year
- Open source interpretability artefacts for R1.☆174Apr 21, 2025Updated last year
- ☆135Oct 28, 2023Updated 2 years ago
- 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.
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆145Sep 14, 2022Updated 3 years ago
- ☆17Feb 14, 2024Updated 2 years ago
- https://transformer-circuits.pub/2025/attribution-graphs/methods.html☆98Mar 27, 2025Updated last year
- ☆10Aug 24, 2023Updated 2 years ago
- ☆76Jul 24, 2025Updated 9 months ago
- ☆59Nov 19, 2024Updated last year
- ☆40Jun 14, 2025Updated 10 months ago
- Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges☆28May 14, 2025Updated 11 months ago
- [NeurIPS 2025@FoRLM] R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search☆17Jan 24, 2026Updated 3 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Codebase for information theoretic shapley values to explain predictive uncertainty.This repo contains the code related to the paperWatso…☆22Jul 4, 2024Updated last year
- GoldFinch and other hybrid transformer components☆46Jul 20, 2024Updated last year
- ☆15Feb 21, 2024Updated 2 years ago
- I read and summarized an academic paper every day for a year.☆11Dec 27, 2020Updated 5 years ago
- I added selfplay functionality to openai gyms☆10Jan 16, 2021Updated 5 years ago
- [NeurIPS 2025] What Makes a Reward Model a Good Teacher? An Optimization Perspective☆43Sep 18, 2025Updated 7 months ago
- Stochastic Parameter Decomposition☆73Updated this week