MLP

also referred to as: mlps

3 statements across 2 episodes · 0 bullish · 2 bearish · 2 people on the record · first statement Jun 6, 2025 by Emmanuel Ameisen · across every show →

Everything said about MLP, oldest first

Jun 6, 2025 neutral
Disclosure
Ameisen: Anthropic's circuit tracing tool ignores attention heads and only decomposes MLPs
“These are just MLPs. So the model has both attention heads and multi-layer perceptions MLPs. We don't just do it. Like we completely ignore attention or like we don't try to decompose it at all. So there's some prompts where like all of the interesting stuff i…”
Emmanuel Ameisen Jun 6, 2025 ▶ 15:56 The Utility of Interpretability — Emmanuel Amiesen
Jun 6, 2025 negative
Assertion Not checkable as stated
Ameisen: Interpretability researchers lack good methods for analyzing attention layers
“So like, I think that right now we have some pretty good solutions for like understanding what's in the residual stream, understanding what's, is it in MLPs? We don't have good solutions for like attention.”
Emmanuel Ameisen Jun 6, 2025 ▶ 1:28:25 The Utility of Interpretability — Emmanuel Amiesen
Aug 3, 2026 negative
Insight
Editing isolated facts in MLP weights fails to update multi-hop downstream reasoning
“So if you know that the best university in the world is Waterloo, then the answer should be Waterloo. But if I wasn't just one-shotting the question and I was to ask it to like, use its knowledge to think and then give me a second answer, or like, should I hir…”
Ali Taha Aug 3, 2026 ▶ 1:40:11 Next 100x in AI: Inference, Networking, & Self-Optimizing Models — Philip Kiely & Ali Taha, Baseten
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.