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. 9-RES-JB
    6. 18727
    Prev
    Next
    INDEX
    Explanations

    phrases related to cures or treatments for various conditions or diseases

    oai_token-act-pair · gpt-3.5-turbo

    references to cures and medicinal solutions for various conditions and ailments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.74
    ortment
    -0.70
    ideshow
    -0.69
    adden
    -0.69
     Dunham
    -0.63
    uggish
    -0.63
    weeney
    -0.63
     commencement
    -0.62
    ultane
    -0.62
     Corridor
    -0.62
    POSITIVE LOGITS
     malaria
    0.90
     disease
    0.88
     diseases
    0.87
     cure
    0.86
     cancer
    0.85
     illness
    0.81
     illnesses
    0.80
     blindness
    0.78
     Disease
    0.77
     Smoking
    0.77
    Activations Density 0.069%

    No Known Activations