© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 20154
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions related to the heart, especially cardiovascular and coronary diseases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cardiac and cardiovascular health conditions

    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
    grounds
    -0.83
    UGC
    -0.82
    Commerce
    -0.82
    onomy
    -0.80
    HOU
    -0.80
    cham
    -0.79
    cott
    -0.79
    lems
    -0.78
    Lens
    -0.74
    Berry
    -0.73
    POSITIVE LOGITS
     artery
    1.22
    iovascular
    1.17
     cardiovascular
    1.05
     arteries
    1.02
     cardiac
    1.01
     hypertension
    0.98
    ascular
    0.96
     vascular
    0.94
     coronary
    0.94
     athe
    0.93
    Activations Density 0.078%

    No Known Activations