© 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. 3075
    Prev
    Next
    INDEX
    Explanations

    repeated phrases starting with "After."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    iology
    -0.70
    ioned
    -0.69
    �
    -0.68
    acements
    -0.67
    CHAT
    -0.65
    cture
    -0.65
    cation
    -0.63
    itialized
    -0.63
    tymology
    -0.62
    エル
    -0.59
    POSITIVE LOGITS
     witnessing
    0.82
     decades
    0.77
     countless
    0.74
     hundreds
    0.73
     witnesses
    0.73
     witness
    0.73
     watching
    0.70
     discovering
    0.69
     listening
    0.69
    noon
    0.68
    Activations Density 0.040%

    No Known Activations