Mechanistic Anomaly Detection Research Update
Interim report on ongoing work on mechanistic anomaly detection
EleutherAI's Research Blog
Previous Posts
Open Source Automated Interpretability for Sparse Autoencoder Features
Building and evaluating an open-source pipeline for auto-interpretability
Experiments in Weak-to-Strong Generalization
Writing up results from a recent project
Free Form Least-Squares Concept Erasure Without Oracle Concept Labels
Achieving even more surgical edits than LEACE without concept labels at inference time.
VINC-S: Closed-form Optionally-supervised Knowledge Elicitation with Paraphrase Invariance
Writing up results from a project from Spring 2023
Pile-T5
Trained T5 on the Pile
Yi-34B, Llama 2, and common practices in LLM training: a fact check of the New York Times
Setting the record straight regarding Yi-34B and Llama 2.
The Foundation Model Development Cheatsheet
Announcing a new resource, the FM Dev Cheatsheet.
Least-Squares Concept Erasure with Oracle Concept Labels
Achieving even more surgical edits than LEACE when we have concept labels at inference time.
Diff-in-Means Concept Editing is Worst-Case Optimal
Explaining a result by Sam Marks and Max Tegmark
The third New England RLHF Hackers Hackathon
Introduction At the third New England RLHF Hackathon, several interesting projects were showcased, each focusing on different aspects of machine learning and reinforcement learning. Participants and those interested in …
Extending the RoPE
How position interpolation, NTK-aware methods, and YaRN extend the context windows of language models using RoPE.
How the Foundation Model Transparency Index Distorts Transparency
Evaluating transparency requires precision.
Llemma: An Open Language Model For Mathematics
ArXiv | Models | Data | Code | Blog | Sample Explorer Today we release Llemma: 7 billion and 34 billion parameter language models for mathematics. The Llemma models were initialized with Code Llama weights, then trained …
The second New England RLHF Hackers Hackathon
Introduction Rekindling the spirit of collaboration, the New England RLHF Hackers (NERH) hosted their second hackathon at Brown University on October 8th, 2023. Stepping up from the success of our inaugural hackathon, …