© 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. 5560
    Prev
    Next
    INDEX
    Explanations

    mentions of specific political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to political events and figures in Egypt

    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
     Sutherland
    -1.08
    Irish
    -1.05
     Leafs
    -0.98
     Conor
    -0.97
     Cork
    -0.95
    /
    -0.95
    Ireland
    -0.94
    Wisconsin
    -0.93
     Loch
    -0.92
     Guam
    -0.92
    POSITIVE LOGITS
     Egyptians
    2.34
    Egypt
    2.33
     Egypt
    2.28
     Egyptian
    2.28
     Cairo
    2.25
     Morsi
    2.23
     Mubarak
    2.18
     Sinai
    1.86
     Pharaoh
    1.82
     Nile
    1.81
    Activations Density 0.253%

    No Known Activations