© 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 EvalsExportsinterp-engineNEWAPI 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. 4265
    Prev
    Next
    INDEX
    Explanations

    medical conditions and related terms

    oai_token-act-pair · gpt-3.5-turbo
    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
    Footnote
    -0.78
    udeau
    -0.71
    usercontent
    -0.71
    taboola
    -0.70
    "},"
    -0.68
    */
    -0.68
    sburg
    -0.67
    inventoryQuantity
    -0.67
     traged
    -0.66
    edin
    -0.62
    POSITIVE LOGITS
     comprised
    1.04
     basically
    0.95
     essentially
    0.93
    formerly
    0.92
     supposed
    0.86
     composed
    0.85
     defined
    0.83
     an
    0.83
     versatile
    0.83
     arguably
    0.83
    Activations Density 0.257%

    No Known Activations