© 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. 0-RES-JB
    11. 8160
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Americans" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to Americans, particularly in contexts relating to demographics and societal issues

    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
    âĶĢ
    -0.73
    cum
    -0.69
    âĶĢâĶĢ
    -0.68
    gie
    -0.67
     suspended
    -0.67
    inator
    -0.66
    âĶĢâĶĢâĶĢâĶĢ
    -0.65
     councillor
    -0.64
     Rune
    -0.64
    robe
    -0.64
    POSITIVE LOGITS
     Americans
    3.69
    Americans
    3.04
     Canadians
    2.47
     Australians
    2.30
     American
    2.07
     Britons
    2.05
     Europeans
    1.96
    American
    1.87
     AMER
    1.87
     Germans
    1.85
    Activations Density 0.019%

    No Known Activations