© 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. 0-RES-JB
    11. 4854
    Prev
    Next
    INDEX
    Explanations

    phrases related to export activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to export activities or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rutherford
    -0.80
    Harris
    -0.72
    pite
    -0.71
    izz
    -0.69
    stakes
    -0.68
     Sandra
    -0.68
     Darrell
    -0.68
    faith
    -0.67
     Donna
    -0.66
     Dor
    -0.66
    POSITIVE LOGITS
     export
    3.89
    export
    2.97
     exporting
    2.91
     exports
    2.76
     exported
    2.70
     Export
    2.68
    Export
    2.32
     import
    2.08
     importing
    1.90
     imported
    1.69
    Activations Density 0.015%

    No Known Activations