© 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. 1290
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "in front of" followed by numerical values

    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
    */(
    -0.97
    ドラ
    -0.76
    黒
    -0.69
    monary
    -0.68
    catentry
    -0.66
     challeng
    -0.65
    َ
    -0.65
    ْ
    -0.63
    falls
    -0.62
    doms
    -0.61
    POSITIVE LOGITS
     divers
    0.60
     Rider
    0.59
     Minor
    0.58
     Shepherd
    0.56
     econom
    0.55
    advertising
    0.55
    ikan
    0.55
    acan
    0.54
     Harbor
    0.53
     Winner
    0.53
    Activations Density 0.033%

    No Known Activations