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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1948
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a foundational concept or rationale

    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
     referen
    -0.67
    Round
    -0.67
    ccording
    -0.65
     physic
    -0.65
    NOR
    -0.64
    Abstract
    -0.63
     Components
    -0.63
    INFO
    -0.63
     proble
    -0.62
     constitu
    -0.61
    POSITIVE LOGITS
    erc
    0.83
    urbed
    0.68
    adra
    0.68
    asking
    0.66
     Kitty
    0.66
    leep
    0.64
    isk
    0.63
    iper
    0.62
    ivan
    0.62
    inished
    0.62
    Activations Density 0.106%

    No Known Activations