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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 675
    Prev
    Next
    INDEX
    Explanations

    positive descriptors associated with size and capability

    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
    ô
    -0.73
    netflix
    -0.71
    ival
    -0.71
     Mehran
    -0.67
    orts
    -0.63
    û
    -0.62
    kered
    -0.62
    anse
    -0.62
    ennis
    -0.61
    kat
    -0.61
    POSITIVE LOGITS
    TN
    0.65
    enance
    0.65
    JV
    0.58
     Celest
    0.58
     ESV
    0.58
    rite
    0.57
     inspectors
    0.56
    Notice
    0.56
     to
    0.55
    ABLE
    0.55
    Activations Density 0.069%

    No Known Activations