© 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. 3196
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ranking or frequency of items

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    wagen
    -0.85
     Flavoring
    -0.70
     Practices
    -0.67
    aught
    -0.67
    wark
    -0.66
    龍喚士
    -0.64
    ifles
    -0.63
    ietal
    -0.61
    saf
    -0.59
    agame
    -0.59
    POSITIVE LOGITS
     prolific
    0.72
     popular
    0.65
     persistent
    0.61
    qus
    0.61
     rem
    0.61
     needy
    0.60
     dependent
    0.59
     depressing
    0.59
     atro
    0.58
     depend
    0.58
    Activations Density 0.047%

    No Known Activations