© 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. 3319
    Prev
    Next
    INDEX
    Explanations

    the word "the" as a frequent and prominent feature in the text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    Loading
    -0.67
    oute
    -0.66
    haps
    -0.65
    apons
    -0.63
    govtrack
    -0.63
    aping
    -0.63
    tering
    -0.62
    poses
    -0.61
    acts
    -0.61
    atal
    -0.61
    POSITIVE LOGITS
     apostle
    0.66
     duo
    0.65
     latter
    0.64
     moment
    0.63
     presence
    0.63
     existence
    0.62
     algorithm
    0.60
     Court
    0.60
     trio
    0.59
     Library
    0.59
    Activations Density 1.049%

    No Known Activations