Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 19185
    Prev
    Next
    INDEX
    Explanations

    the surname "McK" followed by a number that appears to indicate levels of relevance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals with the last name "McK" or "McF"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ³ãĤ¸
    -0.85
     Murdoch
    -0.77
    ãĤª
    -0.75
    ========
    -0.73
    ãĥĵ
    -0.72
    gered
    -0.70
    âĸ¬
    -0.68
    FORE
    -0.68
    omaly
    -0.67
    ãĥĪ
    -0.67
    POSITIVE LOGITS
    intosh
    1.24
    innon
    1.09
    enzie
    0.99
    ellen
    0.96
    erton
    0.95
     McK
    0.93
    arella
    0.93
    azz
    0.92
    haw
    0.90
    arthy
    0.88
    Activations Density 0.005%

    No Known Activations