© 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. 2989
    Prev
    Next
    INDEX
    Explanations

    repeated references to something being specific or notable

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ravings
    -0.80
    rity
    -0.76
    dogs
    -0.72
    DIV
    -0.71
    THER
    -0.68
     Nig
    -0.67
    cellence
    -0.66
    ocious
    -0.65
    umbn
    -0.65
    required
    -0.65
    POSITIVE LOGITS
     scenario
    0.78
     case
    0.72
     shuffle
    0.71
     mish
    0.71
     bookmark
    0.70
     dilemma
    0.69
     variant
    0.68
     lecture
    0.67
     scramble
    0.66
     parting
    0.66
    Activations Density 0.025%

    No Known Activations