© 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. 3126
    Prev
    Next
    INDEX
    Explanations

    repetitions of the phrase "in the first place."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    entials
    -0.79
    avorite
    -0.75
    angan
    -0.73
    uti
    -0.73
    ql
    -0.69
     Marketable
    -0.68
    abilia
    -0.68
     unfocusedRange
    -0.68
     Chart
    -0.66
    hm
    -0.66
    POSITIVE LOGITS
     place
    0.66
     newsp
    0.65
    venants
    0.64
     uproar
    0.63
     Apost
    0.62
     occupation
    0.62
     atheists
    0.59
     adoptive
    0.59
    place
    0.58
    �
    0.57
    Activations Density 0.028%

    No Known Activations