© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 6236
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement, specifically the RCMP (Royal Canadian Mounted Police)

    oai_token-act-pair · gpt-3.5-turbo

    references to law enforcement and governmental figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Negro
    -0.75
    strate
    -0.70
    ÏĢ
    -0.69
    ktop
    -0.69
    glers
    -0.68
    andowski
    -0.65
    ãĥĻ
    -0.64
    bat
    -0.64
    hardt
    -0.63
     Panasonic
    -0.63
    POSITIVE LOGITS
     Trudeau
    0.97
     Saskatchewan
    0.95
    Canada
    0.94
    ipeg
    0.93
     Manitoba
    0.91
     RCMP
    0.90
     Centre
    0.88
     Ottawa
    0.87
     aboriginal
    0.85
     Scotia
    0.84
    Activations Density 0.184%

    No Known Activations