the open
    research
    Contribute
    Back to the reading lists

    Safety, alignment & interpretability· 2017

    Feature Visualization

    Chris Olah (first author) · 2017

    Read the original

    DOI 10.23915/distill.00007OpenAlex W4229494842

    On the reading lists

    Why it matters

    Systematized activation maximization and visualization techniques for understanding learned neural representations.

    Condensed from the expert lists' notes.

    The record

    First released
    2017 (from OpenAlex)
    Citations
    880 citations, as counted by OpenAlex (CC0)
    Named by
    both expert lists
    Score
    0.286 · computed rank 636 · consensus 0.57, must-read 0, citations percentile 0.33 (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.