• Exploring the Biology of LLMs with Circuit Tracing with Emmanuel Ameisen - #727

  • Apr 14 2025
  • Duración: 1 h y 34 m
  • Podcast

Exploring the Biology of LLMs with Circuit Tracing with Emmanuel Ameisen - #727

Escúchala gratis

Ver detalles del espectáculo

  • Resumen

  • In this episode, Emmanuel Ameisen, a research engineer at Anthropic, returns to discuss two recent papers: "Circuit Tracing: Revealing Language Model Computational Graphs" and "On the Biology of a Large Language Model." Emmanuel explains how his team developed mechanistic interpretability methods to understand the internal workings of Claude by replacing dense neural network components with sparse, interpretable alternatives. The conversation explores several fascinating discoveries about large language models, including how they plan ahead when writing poetry (selecting the rhyming word "rabbit" before crafting the sentence leading to it), perform mathematical calculations using unique algorithms, and process concepts across multiple languages using shared neural representations. Emmanuel details how the team can intervene in model behavior by manipulating specific neural pathways, revealing how concepts are distributed throughout the network's MLPs and attention mechanisms. The discussion highlights both capabilities and limitations of LLMs, showing how hallucinations occur through separate recognition and recall circuits, and demonstrates why chain-of-thought explanations aren't always faithful representations of the model's actual reasoning. This research ultimately supports Anthropic's safety strategy by providing a deeper understanding of how these AI systems actually work. The complete show notes for this episode can be found at https://twimlai.com/go/727.
    Más Menos
Más Menos
adbl_web_global_use_to_activate_webcro768_stickypopup

Lo que los oyentes dicen sobre Exploring the Biology of LLMs with Circuit Tracing with Emmanuel Ameisen - #727

Calificaciones medias de los clientes

Reseñas - Selecciona las pestañas a continuación para cambiar el origen de las reseñas.

Reseñas de Audible.com

Opiniones de Amazon
No hay comentarios disponibles