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. 11-RES-JB
    6. 19953
    Prev
    Next
    INDEX
    Explanations

    conditions or diseases that individuals are diagnosed with

    oai_token-act-pair · gpt-3.5-turbo

    medical diagnoses and conditions related to cancer

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -1.18
    uploads
    -0.88
    uder
    -0.84
    isSpecialOrderable
    -0.80
    displayText
    -0.78
    DragonMagazine
    -0.78
    fell
    -0.77
    soType
    -0.76
    essions
    -0.75
    banks
    -0.75
    POSITIVE LOGITS
     schizophrenia
    1.33
     tuberculosis
    1.28
     leukemia
    1.27
     hepatitis
    1.24
     pneumonia
    1.23
     Alzheimer
    1.23
     epilepsy
    1.23
     pancreat
    1.21
     polio
    1.19
     diabetes
    1.19
    Activations Density 0.131%

    No Known Activations