© 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. 1129
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to naming or designating something

    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
    orks
    -0.78
    signed
    -0.77
    sers
    -0.74
    ajo
    -0.73
    istries
    -0.72
    otin
    -0.70
    avers
    -0.70
    onne
    -0.70
    anwhile
    -0.70
    poons
    -0.69
    POSITIVE LOGITS
     Eff
    0.81
     Geh
    0.69
     Stra
    0.66
     McInt
    0.66
     Pebble
    0.65
     Temper
    0.61
     RTX
    0.61
     Precision
    0.59
     Vald
    0.58
     Glen
    0.58
    Activations Density 0.080%

    No Known Activations