© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. MLP Neurons - Layer 6
    4. 5
    Prev
    Next
    Layer 5Layer 7
    INDEX
    Compare
    Explanations

    quotation marks including unicode and ? marks

    Explanation Uploaded by User

    broken or corrupted punctuation

    Explanation Uploaded by User

    question mark

    Explanation Uploaded by User

    question mark, apostrophe and parentheses

    Explanation Uploaded by User

    ?

    Explanation Uploaded by User

    symbols that separate a word from a final s like ' or ?

    Explanation Uploaded by User

    Quotes (including quotes that are parsed incorrectly as unicode or ?)

    Explanation Uploaded by User

    Characters other than ' in places where a possessive apostrophe should be

    Explanation Uploaded by User

    abbreviations, acronyms, and contractions.

    oai_token-act-pair · gpt-4-turbo
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link

    No Known Activations