© 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. 3208
    Prev
    Next
    INDEX
    Explanations

    predicates and states of being that denote existence or characteristics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Tarant
    -0.69
    joined
    -0.69
    lled
    -0.68
    heny
    -0.68
    undai
    -0.66
    ertodd
    -0.66
    mble
    -0.62
     adop
    -0.62
     laun
    -0.61
    brates
    -0.60
    POSITIVE LOGITS
    ANE
    0.77
     easier
    0.76
     kosher
    0.76
     ][
    0.74
     harmful
    0.73
     unanswered
    0.73
     irrelevant
    0.70
    OTT
    0.70
     inconvenient
    0.69
     beneficial
    0.69
    Activations Density 0.125%

    No Known Activations