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

Ep. 7: Interpretability Explorer, Circuit Tracing, and Weight-Sparse Transformers

Welcome to the seventh 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-explorer - 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.

Ep. 6: Assistant Axis, Gemma Scope 2, SAELens, Circuit Tracer, NNsight

Welcome to the sixth 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/assistant-axis - 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.

Ep. 5: A Packed Fall Update

Welcome to the fifth 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/fall-update - 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.

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.

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.