© 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. 3094
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    cule
    -0.60
     pest
    -0.56
     direct
    -0.54
    Witness
    -0.54
    athe
    -0.54
     destro
    -0.53
     closest
    -0.53
     shenan
    -0.53
    mort
    -0.52
     tru
    -0.52
    POSITIVE LOGITS
    050
    0.85
    eca
    0.84
    覚醒
    0.76
    200
    0.68
    2020
    0.68
    ounces
    0.68
    ovember
    0.66
    900
    0.66
    670
    0.66
    750
    0.66
    Activations Density 0.020%

    No Known Activations