© 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. 3227
    Prev
    Next
    INDEX
    Explanations

    instructional phrases or guidelines

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    velt
    -0.72
    uala
    -0.69
    meet
    -0.65
    ospons
    -0.64
    nen
    -0.64
    ividual
    -0.64
    particip
    -0.62
    RM
    -0.61
    payer
    -0.60
    ocobo
    -0.59
    POSITIVE LOGITS
     brighter
    0.65
     contrasting
    0.65
     muted
    0.62
     isolation
    0.60
     budding
    0.60
     fading
    0.60
     shaky
    0.59
     damp
    0.57
    )</
    0.56
     darker
    0.55
    Activations Density 0.732%

    No Known Activations