© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 978
    Prev
    Next
    INDEX
    Explanations

    references to specific people and their identities

    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
     includ
    -0.68
     bait
    -0.63
    uria
    -0.63
    qus
    -0.62
     amuse
    -0.59
    ilater
    -0.59
    ibia
    -0.58
    asse
    -0.58
     tract
    -0.57
    izoph
    -0.57
    POSITIVE LOGITS
    ky
    0.76
    seys
    0.75
    glass
    0.74
    ler
    0.72
    lip
    0.68
    hs
    0.68
    lege
    0.65
    aring
    0.64
    leys
    0.63
    erred
    0.63
    Activations Density 2.742%

    No Known Activations