© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 20379
    Prev
    Next
    INDEX
    Explanations

    mentions of names that start with "McK"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of names related to individuals, particularly those with the prefix "Mc."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gemini
    -0.90
     Bubble
    -0.73
    ãĥ¬
    -0.73
     CBI
    -0.72
     Galileo
    -0.71
     unprotected
    -0.70
    ãĤ¼
    -0.69
    rawdownloadcloneembedreportprint
    -0.68
     Gravity
    -0.67
    ãĥ³ãĤ¸
    -0.66
    POSITIVE LOGITS
    intosh
    1.25
    ellen
    1.05
    ermott
    1.03
    innon
    1.02
    athy
    0.98
    uggets
    0.98
    amara
    0.97
    arthy
    0.97
    eneg
    0.97
    ees
    0.96
    Activations Density 0.026%

    No Known Activations