© 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. 3143
    Prev
    Next
    INDEX
    Explanations

    instances of numerical data and comparisons

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     highs
    -0.80
     failures
    -0.80
     ones
    -0.71
     successes
    -0.70
     bumps
    -0.70
     lows
    -0.69
     aliases
    -0.69
     rentals
    -0.68
     Ones
    -0.68
     milestones
    -0.66
    POSITIVE LOGITS
    FORMATION
    0.71
    ially
    0.71
    ossession
    0.69
    anto
    0.67
    Roaming
    0.64
    otto
    0.64
    ospace
    0.63
    ITNESS
    0.62
    outhern
    0.61
    oster
    0.60
    Activations Density 0.314%

    No Known Activations