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. 10-RES-JB
    6. 22785
    Prev
    Next
    INDEX
    Explanations

    keywords related to various medical conditions and health problems, including serious illnesses, diseases, symptoms, and risk factors

    oai_token-act-pair · gpt-3.5-turbo

    references to serious health conditions and their associated issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.91
    ateurs
    -0.80
    enaries
    -0.71
    ourcing
    -0.71
    selage
    -0.70
     Chau
    -0.70
     DISTRICT
    -0.69
    gee
    -0.69
     warehouses
    -0.69
    UTF
    -0.67
    POSITIVE LOGITS
     ailments
    1.73
     illnesses
    1.71
     symptoms
    1.71
     illness
    1.68
     diseases
    1.67
     disease
    1.60
     ail
    1.56
     disorders
    1.50
     complications
    1.46
     debilitating
    1.43
    Activations Density 0.224%

    No Known Activations