© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1273
    Prev
    Next
    INDEX
    Explanations

    encoded characters and symbols in the text

    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
    heny
    -0.70
    Bow
    -0.68
    atos
    -0.66
    ua
    -0.64
    abal
    -0.62
    anu
    -0.60
     Leilan
    -0.60
    ius
    -0.60
    ucer
    -0.59
    UA
    -0.59
    POSITIVE LOGITS
    ocl
    0.66
    rican
    0.64
    esters
    0.61
    arent
    0.60
    psey
    0.60
    ery
    0.60
    earance
    0.60
    reys
    0.59
    ished
    0.59
     groom
    0.58
    Activations Density 1.235%

    No Known Activations