the open
    research
    Contribute
    Back to the reading lists

    Safety, alignment & interpretability· 2017

    Network Dissection: Quantifying Interpretability of Deep Visual Representations

    David Bau (first author) · 2017

    Read the original

    DOI 10.1109/cvpr.2017.354arXiv 1704.05796OpenAlex W2610018085

    On the reading lists

    Why it matters

    Introduced systematic measurement of alignment between individual neural units and semantic concepts.

    Condensed from the expert lists' notes.

    The record

    First released
    2017 (from arXiv 1704.05796)
    Citations
    1,859 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Score
    0.452 · computed rank 290 · consensus 0.85, must-read 0, citations percentile 0.564 (2010s · safety), awards 0, existing lists 0. Method

    Data sources

    Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.