Rumbelow: Interpretability turns neural networks into scientific discovery tools
Jessica Rumbelow · ⚡️Automating Scientific Discovery - Jessica Rumbelow, Leap Labs · Nov 2, 2025 · at 2:29
Dr. Jessica Rumbelow, founder of Leap Labs, explains how mechanistic interpretability allows AI to uncover novel scientific patterns that humans cannot perceive.
0:00 / 0:19exact quote · 19.7s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“If you've got really good interp, you can start to reframe neural networks, not as just a tool for automating things that we already know how to do, but as a tool for discovery, as like a lens through which you can see patterns in data that would otherwise Be hidden from you.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Jessica Rumbelow
Rumbelow: Leap Labs' Discovery Engine Automates Novel Scientific Discovery via Interpretability
“Discovery Engine is an end-to-end system, takes in arbitrary scientific data set, automatically trains a bunch of neural networks on it, and then We systematically, with our interpretability methods, which is the real secret extract the patterns that have been…”
Rumbelow: arXiv Is Filling With Plausible but Unverified AI Papers
“I'm actually really worried about this because I think we're already seeing archive and other online repositories and... Submissions too, full of these very, very plausible papers. That may or may not be true. And like at that point, what good is the, is our s…”
Rumbelow: Leap Labs Discovered Novel Predictive Markers for Tumor-Reactive T Cells
“And we found basically novel markers that are quite predictive of this. And these novel markers were not what we expected them to be.”
Rumbelow: LLMs Are Ill-Suited for Large Numeric Datasets
“Language models are just that, right? They're models of language. They are not particularly well suited for understanding arbitrary, you know, like big numeric data sets.”
Rumbelow: Standalone Claude Opus Hallucinated Materials Science Data Findings
“So, so Claude, lovely Claude. I'm sorry Claude, but you did a terrible job. It hallucinated some stuff. It made some like big sweeping over, over generalizations. It like over indexed the few outliers. Like, it's fine. It's not Claude's fault. Like Claude is j…”
Rumbelow: Multimodal analysis is impossible without fine labeling or interpretability
“It's largely impossible to do good data analysis on multimodal data of this kind, unless you have really fine grained labeling of your images. For example, which is just very, very burdensome, but obviously deep learning, we can let the model figure out its ow…”