The Babble: A Neuronpedia Podcast (by NotebookLM)

Neuronpedia

The Babble is the podcast form of Neuronpedia's blog, The Residual Stream. Episodes are generated by feeding NotebookLM the latest post from https://neuronpedia.org/blog. Posts are about mechanistic interpretability (the science of understanding AI model internals) and the newest Neuronpedia features. Neuronpedia (neuronpedia.org) is world's first hosted mechanistic interpretability platform - it's used by researchers, labs, and companies for understanding and steering the internals of AI models. Contact us for collaborations/feedback/questions at johnny@neuronpedia.org.

에피소드

  1. 8월 6일

    Ep. 4: Interpretability Orgs, Assemble! 📜🧠🔥🗽🔍

    Welcome to the fourth episode of The Babble: a Neuronpedia podcast. Each episode is generated by feeding NotebookLM the latest post from Neuronpedia's blog, The Residual Stream. Episode Notes: - This episode is based off of the post: https://www.neuronpedia.org/blog/interp-orgs-assemble - Hosts mention "EleutherAI's 'cult-training' library" - they actually mean "clt-training" 😅 - Disclaimer: The AI hosts are correct about Neuronpedia's features and intentions, but their optimism may make them sound overly promotional, despite our specific notes to not do so. Neuronpedia (neuronpedia.org) is world's first hosted mechanistic interpretability platform - it's used by researchers, labs, and companies for understanding and steering the internals of AI models. Contact us for collaborations/feedback/questions at johnny@neuronpedia.org.

    5분

  2. 6월 13일

    Ep. 3: Circuit Tracer x Anthropic, plus a New Auto-Interp Method

    Welcome to the third episode of The Babble: a Neuronpedia podcast. Each episode is generated by feeding NotebookLM the latest post from Neuronpedia's blog, The Residual Stream. Episode Notes: - This episode is based off of the post: https://www.neuronpedia.org/blog/circuit-tracer - Disclaimer: The AI hosts are correct about Neuronpedia's features and intentions, but their optimism may make them sounds a little too marketing-y than we intend, despite our specific notes to not do so. Neuronpedia (neuronpedia.org) is world's first hosted mechanistic interpretability platform - it's open source and used by researchers, labs, and companies for understanding and steering the internals of AI models. Contact us for collaborations/feedback/questions at johnny@neuronpedia.org.

    13분

  3. 4월 21일

    Ep. 2: New Features, Tools, and Our Podcast: The Babble

    Welcome to the second episode of The Babble: a Neuronpedia podcast. Each episode is generated by feeding NotebookLM the latest post from Neuronpedia's blog, The Residual Stream. This episode is based off of the post: https://www.neuronpedia.org/blog/bunch-of-updates Disclaimer: The AI hosts are correct about Neuronpedia's features and intentions, but their optimism may make them sounds a little too marketing-y than we intended, even though we ask them specifically to be less salesy. Neuronpedia (neuronpedia.org) is world's first hosted mechanistic interpretability platform - it's used by researchers, labs, and companies for understanding and steering the internals of AI models. Contact us for collaborations/feedback/questions at johnny@neuronpedia.org.

    16분

  4. 4월 18일

    Ep. 1: Open Sourcing Neuronpedia and Datasets

    Welcome to the first episode of The Babble: a Neuronpedia podcast. Each episode is generated by feeding NotebookLM the latest post from Neuronpedia's blog, The Residual Stream. Episode Notes: - This episode is based off of the post: https://www.neuronpedia.org/blog/neuronpedia-is-now-open-source - Content: Starts with an introduction, then a general overview on what Neuronpedia is, and finally summarizes the blog post's main points about open sourcing. - Disclaimer: The AI hosts are correct about Neuronpedia's features and intentions, but their optimism may make them sounds a little too marketing-y than we intended. Neuronpedia (neuronpedia.org) is world's first hosted mechanistic interpretability platform - it's used by researchers, labs, and companies for understanding and steering the internals of AI models. Contact us for collaborations/feedback/questions at johnny@neuronpedia.org.

    13분
  • 4개의 에피소드

평가 및 리뷰

5
최고 5점
2개의 평가

소개

The Babble is the podcast form of Neuronpedia's blog, The Residual Stream. Episodes are generated by feeding NotebookLM the latest post from https://neuronpedia.org/blog. Posts are about mechanistic interpretability (the science of understanding AI model internals) and the newest Neuronpedia features. Neuronpedia (neuronpedia.org) is world's first hosted mechanistic interpretability platform - it's used by researchers, labs, and companies for understanding and steering the internals of AI models. Contact us for collaborations/feedback/questions at johnny@neuronpedia.org.

정보