© 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. 3144
    Prev
    Next
    INDEX
    Explanations

    references to devices and platforms

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     prefers
    -0.72
     smuggled
    -0.63
     raids
    -0.63
    avers
    -0.62
     contracting
    -0.61
    llers
    -0.59
     resists
    -0.59
     dresses
    -0.59
    ampunk
    -0.59
     dysph
    -0.59
    POSITIVE LOGITS
     CrossRef
    0.69
    ゼウス
    0.69
    200000
    0.68
    ????????
    0.68
    assetsadobe
    0.66
    ��
    0.66
     DPR
    0.65
    66666666
    0.64
    itatively
    0.62
     Millennium
    0.61
    Activations Density 0.011%

    No Known Activations