© 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
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 3003
    Prev
    Next
    INDEX
    Explanations

    phrases indicating degrees or qualities of various attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ventus
    -0.80
    worthiness
    -0.67
    ships
    -0.67
    ipers
    -0.66
    fw
    -0.66
    bah
    -0.66
    iveness
    -0.66
    riors
    -0.65
    terness
    -0.65
    iness
    -0.65
    POSITIVE LOGITS
     eighteenth
    0.73
     nineteenth
    0.67
     centuries
    0.67
    UTC
    0.66
     twentieth
    0.65
     bothering
    0.63
     millennia
    0.62
    erous
    0.60
    elfth
    0.59
     )]
    0.58
    Activations Density 0.135%

    No Known Activations