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. 1897
    Prev
    Next
    INDEX
    Explanations

    terms related to blood flow and medical conditions such as high blood pressure and diabetes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to blood and its associated measurements or conditions

    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
    lvl
    -0.77
    owered
    -0.72
    cffffcc
    -0.70
    ovie
    -0.69
    ilitary
    -0.68
     rall
    -0.68
    olicy
    -0.68
    oÄŁ
    -0.67
    odder
    -0.66
    ggles
    -0.65
    POSITIVE LOGITS
     glucose
    1.17
     clot
    1.06
     vessels
    1.04
     cholesterol
    1.01
    flow
    0.99
     transf
    0.98
     sugars
    0.95
     endot
    0.95
     pressure
    0.94
    thirst
    0.94
    Activations Density 0.019%

    No Known Activations