© 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. 306
    Prev
    Next
    INDEX
    Explanations

    content related to Scandinavian countries, with a focus on Sweden

    oai_token-act-pair · gpt-3.5-turbo
    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
     Mayweather
    -1.07
    BAT
    -1.03
     Floyd
    -1.01
     Cavaliers
    -0.95
    CLE
    -0.92
    Louis
    -0.89
     Richmond
    -0.88
     Cavs
    -0.86
    MAC
    -0.85
     Pryor
    -0.84
    POSITIVE LOGITS
     Swedish
    2.34
     Sweden
    2.28
     Swed
    2.23
     Nordic
    2.21
     Icelandic
    2.17
     Scandinavian
    2.14
     Norwegian
    2.13
     Scandinav
    2.12
     Stockholm
    2.11
     Denmark
    2.05
    Activations Density 0.652%

    No Known Activations