Construct · 1 fields · 1 citations

polysemanticity: a standalone construct

One name. One construct. A landmark on the map.

● anchor · a standalone construct Nearest construct by meaning·not indexed
polysemanticity1 CONSTRUCTPolysemanticityOLAH · EXPLAINABLE ARTIFICIAL

A single standalone construct; nearby constructs are located against it in the Collider. Tap a field for its definition, unit, and measures.

Explainable artificial intelligence

single neurons that respond to several unrelated features, which makes reading a network one neuron at a time misleading.

In explainable artificial intelligence, polysemanticity refers to single neurons that respond to several unrelated features, which makes reading a network one neuron at a time misleading. This meaning comes from Olah (2020) in Distill.[1]

Unit
Recovery means
Measured by

Next

Run it through the Collider, or take the citations with you.

See how polysemanticity sits against neighbouring constructs in the Collider, or export every reference on this page in one click.

Open in ColliderExport BibTeXReport this entry

Nearby constructs

mechanistic interpretability1 fields · 1 citationsanchor · a standalone constructexplainable artificial intelligence1 fields · 1 citationsanchor · a standalone constructintelligence6 fields · 14 citationsjingle · one name, six constructs

References

  1. Olah, C., Cammarata, N., Schubert, L., Goh, G., Petrov, M., & Carter, S. (2020). Zoom In: An Introduction to Circuits. Distill, 5(3). https://doi.org/10.23915/distill.00024.001

Cited on this page?

Confirm your construct, or correct us.

If your work is cited behind one of these entries, you know better than we do whether we captured the meaning right. Confirm it, suggest an edit, or dispute it, and your name goes on the entry as an author who has checked it, linked to your ORCID.

Claim your construct