Categories: FAANG

Language models can explain neurons in language models

We use GPT-4 to automatically write explanations for the behavior of neurons in large language models and to score those explanations. We release a dataset of these (imperfect) explanations and scores for every neuron in GPT-2.
AI Generated Robotic Content

Recent Posts

5 Architectural Patterns for Persistent Memory and State in AI Agents

Memory & State For AI Agents Building an AI agent can be tricky. Keeping it…

14 hours ago

Teaching LLMs to Update Beliefs for Efficient Long-Horizon Interaction

Overview of ABBEL compared to traditional recursive summarization. Beliefs replace the full interaction history as…

14 hours ago

GH-ESD: Grounded Hypothesis-Driven Error Slice Discovery for Instance-Level Vision Tasks

Systematic failures of vision models on semantically coherent subsets, known as error slices, reveal limitations…

14 hours ago

AI Sovereignty is Your Alpha: How to Avoid Transferring Your Alpha to a Hosted Model Provider

Use of third party AI model services poses significant risk to your alpha. Without sovereign…

14 hours ago

Beyond RAG: Task-aware knowledge compression for enterprise AI on AWS

If you’re using Retrieval-Augmented Generation (RAG) for complex analytical tasks that span hundreds of documents,…

14 hours ago

France Records Its First-Ever Pyrocumulonimbus Cloud Amid Record-Smashing Fires

Extreme fire conditions on the ground have created unprecedented conditions in the atmosphere.

15 hours ago