© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 910
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "periscopes" or related terms

    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
    ills
    -0.64
     Mack
    -0.63
    doors
    -0.62
    soDeliveryDate
    -0.60
    acements
    -0.60
    riers
    -0.60
    uff
    -0.59
    fc
    -0.59
     admins
    -0.57
     muff
    -0.57
    POSITIVE LOGITS
    aris
    0.83
    stitial
    0.73
    Origin
    0.68
    comes
    0.68
    apses
    0.68
    eni
    0.67
    enic
    0.64
    roleum
    0.64
    urable
    0.63
    atari
    0.62
    Activations Density 0.028%

    No Known Activations