© 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. 14182
    Prev
    Next
    INDEX
    Explanations

    mentions of government departments and policies

    oai_token-act-pair · gpt-3.5-turbo

    key governmental departments and their functions

    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
     Canadians
    -1.04
     Winnipeg
    -1.00
     Saskatchewan
    -0.99
     aboriginal
    -0.95
     Hawai
    -0.94
     Calgary
    -0.93
     Trudeau
    -0.91
     CFL
    -0.89
     RCMP
    -0.89
     Canadian
    -0.87
    POSITIVE LOGITS
    ottenham
    1.09
     Leicester
    1.09
     Midlands
    1.09
     Stoke
    1.06
     Norwich
    1.05
     Middles
    1.03
    Liverpool
    1.02
     Tottenham
    1.02
     Yorkshire
    1.00
     Birmingham
    0.99
    Activations Density 0.618%

    No Known Activations