© 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. 3083
    Prev
    Next
    INDEX
    Explanations

    terms related to small quantities or minimal representations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    EY
    -0.76
    amy
    -0.73
    anos
    -0.71
    peak
    -0.67
    pas
    -0.65
    anism
    -0.63
    orp
    -0.63
    conserv
    -0.62
    illation
    -0.62
    emin
    -0.61
    POSITIVE LOGITS
     chance
    0.68
     resemblance
    0.68
     payday
    0.64
     violation
    0.63
     miscarriage
    0.62
     Mun
    0.61
    verages
    0.60
     Lutheran
    0.60
     chapter
    0.60
     simulac
    0.58
    Activations Density 0.097%

    No Known Activations