© 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. 3330
    Prev
    Next
    INDEX
    Explanations

    instances of specific high-stakes discussions or controversies

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    soever
    -0.63
    References
    -0.60
    sheets
    -0.60
    Activ
    -0.60
    minist
    -0.59
     congratulations
    -0.59
    reviewed
    -0.58
    dit
    -0.57
    ework
    -0.57
    REL
    -0.56
    POSITIVE LOGITS
     �
    0.68
     Smy
    0.65
     cradle
    0.60
    veland
    0.60
     recorder
    0.60
     mold
    0.59
     rarity
    0.59
     msec
    0.59
    orage
    0.58
     Oval
    0.57
    Activations Density 0.189%

    No Known Activations