person

Martin Wattenberg

Harvard; ex-Google PAIR; visualization for ML

Harvard professor and former senior research scientist at Google, where he co-founded the People + AI Research initiative. Long-time pioneer of interpretability through visualization.

current Gordon McKay Professor of Computer Science, Harvard University

past Senior Research Scientist, Google Research (PAIR)

homepage

Strategy positions

Interpretability betendorses

Mechanistic interpretability is necessary and sufficient to know models are safe

Argues visualization is a primary research method for understanding modern neural networks, not a presentation layer, and that the field's safety guarantees rise and fall with the depth of that understanding.

If we can't see what models are doing, we can't trust them. Visualization is fundamental to building justified confidence in ML systems.

¶ articleMartin Wattenberg, Harvard· Harvard SEAS· 2023· faithful paraphrase

Closest strategy neighbours

by jaccard overlap

Other people whose strategy tags overlap with Martin Wattenberg's. Overlap is on tag identity, not stance; opposites can show up if they reference the same tags.

Asma Ghandeharioun
shared 1 · J=1.00
Google DeepMind; 'Patchscopes' for LLM interpretability
Chris Olah
shared 1 · J=1.00
Anthropic interpretability co-founder; inventor of modern mech interp
Cynthia Rudin
shared 1 · J=1.00
Duke professor; interpretable ML pioneer
David Bau
shared 1 · J=1.00
Northeastern; mechanistic interpretability of LLMs
Fernanda Viégas
shared 1 · J=1.00
Harvard; ex-Google PAIR; data visualization
Jacob Andreas
shared 1 · J=1.00
MIT NLP; language models as belief reports

Record last updated 2026-04-25.