© 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. 10-RES-JB
    11. 10259
    Prev
    Next
    INDEX
    Explanations

    keywords related to geographical locations or institutions, particularly those in or associated with the western region

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations, particularly states and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eur
    -0.74
     UNESCO
    -0.73
     selfie
    -0.73
     globalization
    -0.71
    obbies
    -0.70
    enegger
    -0.69
    staking
    -0.67
    netflix
    -0.65
    english
    -0.64
     geop
    -0.63
    POSITIVE LOGITS
     Bulldogs
    0.90
     Carolina
    0.90
    Minnesota
    0.85
     Illinois
    0.85
    Force
    0.83
    brook
    0.82
    mitting
    0.81
     Michigan
    0.80
    olver
    0.80
     Athletic
    0.80
    Activations Density 0.092%

    No Known Activations