Lists (2)
Stars
Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparen…
Compare how different AI models perform on Thailand’s standardized exams
⬤▗▚▚▚ Web-based online rhythm action game. Based on HTML5 technologies, React, Redux and Pixi.js.
[ICML 2025] "From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?"
[ICLR 2025 Workshop] "Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models"
For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.
Report issues and discuss improvements / feature requests around TETR.IO
Efficient Dictionary Learning with Switch Sparse Autoencoders (SAEs)
Integrate the DeepSeek API into popular softwares
Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
Repository for the "Chain-of-Thought Reasoning In The Wild Is Not Always Faithful" paper
Materials for EACL2024 tutorial: Transformer-specific Interpretability
Probing the knowledge about recursive Noun Phrases (NPs) in state-of-the-art language models.
Code and data accompanying our paper on arXiv "Faithful Chain-of-Thought Reasoning".
"Improving Mathematical Reasoning with Process Supervision" by OPENAI
APPS: Automated Programming Progress Standard (NeurIPS 2021)
A (deprecated) framework for building exercises to work with Khan Academy.