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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1057
    Prev
    Next
    INDEX
    Explanations

    specific elements related to sensory experiences and unique characteristics of objects

    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
    Reward
    -0.72
     Dram
    -0.64
    iton
    -0.60
     DOI
    -0.57
    Rew
    -0.57
     Horowitz
    -0.57
    �
    -0.56
     Trem
    -0.55
     Guerrero
    -0.55
    >>>>>>>>
    -0.55
    POSITIVE LOGITS
     surround
    0.80
    present
    0.77
     abound
    0.77
     lurking
    0.77
     accompany
    0.76
     present
    0.74
     avail
    0.73
     forthcoming
    0.73
     lying
    0.73
     emerging
    0.71
    Activations Density 0.650%

    No Known Activations