© 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. 1863
    Prev
    Next
    INDEX
    Explanations

    phrases related to regression or reverting to previous states

    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
    ema
    -0.67
    osi
    -0.63
    oms
    -0.60
    oS
    -0.60
     cohesion
    -0.60
    ome
    -0.59
    ello
    -0.57
    女
    -0.57
    rament
    -0.57
    uana
    -0.56
    POSITIVE LOGITS
     past
    1.18
     previous
    1.12
     previously
    1.08
     Previously
    1.05
     ago
    0.99
     ancestors
    0.98
     earlier
    0.97
    Previously
    0.97
     1938
    0.95
     predecessors
    0.94
    Activations Density 1.769%

    No Known Activations