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

    Neuronpedia

    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. 10-RES-JB
    11. 1438
    Prev
    Next
    INDEX
    Explanations

    patterns related to mathematical equations

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and their associations, often related to sports statistics and dates

    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
    20439
    -0.87
    nces
    -0.80
    peria
    -0.78
    foundland
    -0.76
    Austral
    -0.74
    anmar
    -0.71
    jer
    -0.71
    wire
    -0.70
    LER
    -0.70
    Jun
    -0.69
    POSITIVE LOGITS
     Submit
    0.83
     Categories
    0.74
     Misc
    0.73
     Quantity
    0.70
     Personal
    0.70
     11
    0.69
     WARNING
    0.69
     10
    0.69
     Supp
    0.68
     =================
    0.67
    Activations Density 0.032%

    No Known Activations