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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2117
    Prev
    Next
    INDEX
    Explanations

    phrases that describe a wide range of topics or subjects

    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
    naires
    -0.65
     Nasa
    -0.64
    ildo
    -0.62
     Lum
    -0.60
     Goldman
    -0.59
     independ
    -0.58
     Mars
    -0.57
     Pyth
    -0.56
    olean
    -0.56
     Meier
    -0.55
    POSITIVE LOGITS
    ranging
    0.78
    mad
    0.76
    med
    0.71
    puff
    0.70
    vo
    0.69
    should
    0.68
    spect
    0.68
    facing
    0.67
    bottom
    0.66
    baugh
    0.66
    Activations Density 0.024%

    No Known Activations