© 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. 2336
    Prev
    Next
    INDEX
    Explanations

    references to timing and sequence, particularly the word "before" and mentions of numerical contexts

    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
    ggles
    -0.68
    ゼウス
    -0.64
     Detected
    -0.64
     Appears
    -0.63
    advertisement
    -0.63
     sidx
    -0.63
    conservancy
    -0.62
    Probably
    -0.61
    cffffcc
    -0.60
     VIDEOS
    -0.60
    POSITIVE LOGITS
     they
    1.00
     we
    0.98
     it
    0.90
     there
    0.90
     you
    0.84
     he
    0.83
     she
    0.82
     I
    0.80
     these
    0.79
     nobody
    0.73
    Activations Density 2.004%

    No Known Activations