© 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. 3326
    Prev
    Next
    INDEX
    Explanations

    segments of text that indicate formal or structured information

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     proximity
    -0.62
     branch
    -0.61
     nucleus
    -0.60
     close
    -0.60
     conflicted
    -0.59
     dimin
    -0.59
     tested
    -0.59
     LB
    -0.58
     cited
    -0.58
     chained
    -0.57
    POSITIVE LOGITS
    Warning
    0.99
    Eight
    0.92
    Ever
    0.90
    TOR
    0.90
    Following
    0.90
    Portland
    0.90
    Aut
    0.89
    Guest
    0.89
    Princ
    0.89
    Dear
    0.88
    Activations Density 0.150%

    No Known Activations