© 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. 3013
    Prev
    Next
    INDEX
    Explanations

    references to training activities or programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abo
    -0.72
    mental
    -0.71
     largeDownload
    -0.69
    trigger
    -0.68
    blocking
    -0.67
    minimum
    -0.65
    ��
    -0.65
    fried
    -0.65
    ��
    -0.64
    ATA
    -0.62
    POSITIVE LOGITS
     Obst
    0.68
     anniversary
    0.65
     grounds
    0.65
     occasion
    0.64
     discrepancy
    0.63
     Grounds
    0.62
     accident
    0.60
     offence
    0.59
     tables
    0.58
     Bung
    0.58
    Activations Density 0.073%

    No Known Activations