© 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. 2583
    Prev
    Next
    INDEX
    Explanations

    mentions of the Canadian Prime Minister Justin Trudeau

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Justin Trudeau

    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
     io
    -0.67
    vern
    -0.64
    EE
    -0.64
    tyard
    -0.63
     bat
    -0.62
    hot
    -0.61
    AE
    -0.60
    1111
    -0.60
    sect
    -0.59
    BB
    -0.59
    POSITIVE LOGITS
     Trudeau
    3.93
    udeau
    2.67
     Mulcair
    2.41
     Liberals
    1.90
     Turnbull
    1.78
     NDP
    1.75
     Canadians
    1.71
     Harper
    1.63
    Canada
    1.56
     RCMP
    1.55
    Activations Density 0.013%

    No Known Activations