© 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. 3-RES-JB
    11. 15060
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions, particularly strokes

    oai_token-act-pair · gpt-3.5-turbo

    references to strokes and related medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     proprietary
    -0.75
    guyen
    -0.73
    %"
    -0.71
    gemony
    -0.67
    eanor
    -0.65
     assimil
    -0.62
    agree
    -0.62
     expend
    -0.62
    skirts
    -0.62
     scraps
    -0.62
    POSITIVE LOGITS
     stroke
    1.32
     strokes
    1.04
    stroke
    0.92
     Stro
    0.85
    manship
    0.83
    weed
    0.74
    FIELD
    0.69
    iovascular
    0.69
    fish
    0.67
    wheel
    0.67
    Activations Density 0.014%

    No Known Activations