www.lesswrong.com/posts/skKYznZyRtN87tHbB/neuronpedia

This statement is outdated and contradicted by Neuronpedia’s later official materials.

• In Neuronpedia’s March 25, 2024 announcement post, the authors explicitly say: “Neuronpedia is a platform for mechanistic interpretability research. It was previously focused on crowdsourcing explanations of neurons, but we've pivoted to accelerating researchers for Sparse Autoencoders (SAEs) by hosting models, feature dashboards, data visualizations, tooling, and more.”
• Neuronpedia’s current homepage likewise describes it as “an open source interpretability platform” where users can “Explore, steer, and experiment on AI models,” not as an AI-safety game.
• The homepage also says Neuronpedia now supports “probes, latents/features, custom vectors, concepts, and more,” which directly conflicts with the narrower description that it documents and explains “each neuron.”

So while this may have described an early 2023 version of the project, it is not an accurate description of what Neuronpedia is now.