© 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. 11-RES-JB
    11. 5925
    Prev
    Next
    INDEX
    Explanations

    keywords related to international relationships, economics, diplomacy, and governmental positions

    oai_token-act-pair · gpt-3.5-turbo

    references to Canada’s international standing and economic relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Issa
    -0.79
     Carlo
    -0.71
     Arpaio
    -0.69
    paio
    -0.68
    released
    -0.67
    aiman
    -0.65
    raged
    -0.64
     Anon
    -0.63
     rumors
    -0.63
     Pryor
    -0.63
    POSITIVE LOGITS
     competitiveness
    1.08
    ivot
    1.06
     prosperity
    1.04
     greatness
    1.00
     superpower
    0.99
     pivot
    0.99
     exports
    0.95
     Nato
    0.94
     strengths
    0.93
     export
    0.92
    Activations Density 0.414%

    No Known Activations