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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 369
    Prev
    Next
    INDEX
    Explanations

    words related to famous individuals with names ending in '-baugh' or '-baughh', particularly focusing on sports figures

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent individuals in sports and politics

    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
    reens
    -0.79
    ivities
    -0.77
    uct
    -0.75
    ivity
    -0.74
    NetMessage
    -0.73
    lihood
    -0.71
    phis
    -0.70
    ivism
    -0.70
    semble
    -0.70
    orea
    -0.69
    POSITIVE LOGITS
    etz
    0.76
     Harbaugh
    0.72
    zag
    0.67
    artney
    0.66
    baugh
    0.64
     McMahon
    0.63
     Laden
    0.62
     Stack
    0.61
    bert
    0.60
     Canaver
    0.60
    Activations Density 0.026%

    No Known Activations