© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 3173
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "first," particularly in chronological contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    alys
    -0.86
    otype
    -0.76
    adal
    -0.72
    abul
    -0.72
    Availability
    -0.67
    ér
    -0.66
    aye
    -0.64
    Http
    -0.64
    Reward
    -0.64
    mk
    -0.64
    POSITIVE LOGITS
     floors
    0.66
     Archdemon
    0.63
     glim
    0.61
     taped
    0.60
     teasp
    0.60
    oons
    0.59
     Dumb
    0.59
     Fires
    0.59
     handc
    0.58
     quart
    0.58
    Activations Density 0.031%

    No Known Activations