Construct · 1 fields · 1 citations

knowledge neurons: a standalone construct

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

● anchor · a standalone construct Nearest construct by meaning·not indexed

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

feed-forward neurons in a pretrained transformer whose activation is linked to expressing a specific relational fact.

In explainable artificial intelligence, knowledge neurons refers to feed-forward neurons in a pretrained transformer whose activation is linked to expressing a specific relational fact. This meaning comes from Dai (2022) in Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).[1]

Unit
Recovery means
Measured by

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

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

Open in Collider Export BibTeX Report this entry

Nearby constructs

activation4 fields · 4 citationsjingle · one word, four constructs association4 fields · 4 citationsjingle · one word, four constructs explainable artificial intelligence1 fields · 1 citationsanchor · a standalone construct

References

Dai, D., Dong, L., Hao, Y., Sui, Z., Chang, B., & Wei, F. (2022). Knowledge Neurons in Pretrained Transformers. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). https://doi.org/10.18653/v1/2022.acl-long.581

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