© 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. 3084
    Prev
    Next
    INDEX
    Explanations

    key elements related to visual descriptions or iconic representations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    pointers
    -0.77
    poor
    -0.72
    sheets
    -0.68
    quartered
    -0.67
     holes
    -0.67
     accumulate
    -0.65
    hews
    -0.65
     heals
    -0.65
    flush
    -0.65
    Eventually
    -0.65
    POSITIVE LOGITS
     Kau
    0.76
     Polo
    0.75
    ITH
    0.73
     Volcano
    0.73
    ICAN
    0.72
     Orange
    0.72
     NAV
    0.71
     Ing
    0.70
    ELF
    0.70
     Ecology
    0.70
    Activations Density 1.633%

    No Known Activations