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. 0-RES-JB
    6. 8667
    Prev
    Next
    INDEX
    Explanations

    terms related to physical medical conditions, especially strokes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "stroke", particularly in a medical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tradable
    -0.84
    ér
    -0.78
    vin
    -0.73
    ifi
    -0.73
    és
    -0.72
    imon
    -0.71
    qa
    -0.68
    host
    -0.66
    / 
    -0.63
    iesel
    -0.63
    POSITIVE LOGITS
     stroke
    4.33
     strokes
    2.95
    stroke
    2.29
     Stro
    2.03
     stride
    1.07
     swipe
    1.03
     wink
    1.02
     piston
    0.96
     coronary
    0.95
     thickness
    0.92
    Activations Density 0.019%

    No Known Activations