EleutherAI Blog · 实时热榜

Reward Hacking Resarch Update blog.eleuther.ai

Pretraining Data Filtering for Open-Weight AI Safety blog.eleuther.ai

Attention Probes blog.eleuther.ai

The Common Pile v0.1 blog.eleuther.ai

Product Key Memory Sparse Coders blog.eleuther.ai

SAEs trained on the same data don’t learn the same features blog.eleuther.ai

The Practitioner's Guide to the Maximal Update Parameterization blog.eleuther.ai

Open Source Automated Interpretability for Sparse Autoencoder Features blog.eleuther.ai

Experiments in Weak-to-Strong Generalization blog.eleuther.ai

Free Form Least-Squares Concept Erasure Without Oracle Concept Labels blog.eleuther.ai

Pile-T5 blog.eleuther.ai

Least-Squares Concept Erasure with Oracle Concept Labels blog.eleuther.ai

Diff-in-Means Concept Editing is Worst-Case Optimal blog.eleuther.ai

Extending the RoPE blog.eleuther.ai

How the Foundation Model Transparency Index Distorts Transparency blog.eleuther.ai

Llemma: An Open Language Model For Mathematics blog.eleuther.ai

Contributor Spotlight: Mohammad Aflah Khan blog.eleuther.ai

EleutherAI's Thoughts on the EU AI Act blog.eleuther.ai

Minetester: A fully open RL environment built on Minetest blog.eleuther.ai

🐶Safetensors audited as really safe and becoming the default blog.eleuther.ai

Alignment Research @ EleutherAI blog.eleuther.ai

Transformer Math 101 blog.eleuther.ai

Exploratory Analysis of TRLX RLHF Transformers with TransformerLens blog.eleuther.ai

EleutherAI Second Retrospective: The long version blog.eleuther.ai

The View from 30,000 Feet: Preface to the Second EleutherAI Retrospective blog.eleuther.ai

Announcing GPT-NeoX-20B blog.eleuther.ai

Multiple Choice Normalization in LM Evaluation blog.eleuther.ai

What A Long, Strange Trip It's Been: EleutherAI One Year Retrospective blog.eleuther.ai

Why Release a Large Language Model? blog.eleuther.ai

On the Sizes of OpenAI API Models blog.eleuther.ai