© 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. 1-RES-JB
    11. 17546
    Prev
    Next
    INDEX
    Explanations

    references to the country Sweden

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Sweden

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mayweather
    -0.73
    sbm
    -0.67
     vig
    -0.61
     fasting
    -0.61
     cultivation
    -0.61
    ours
    -0.60
    arial
    -0.60
    onel
    -0.59
     poppy
    -0.59
     homosexual
    -0.58
    POSITIVE LOGITS
    borg
    1.34
    sson
    1.21
     Sweden
    1.14
    å
    1.08
     Swed
    0.96
    ö
    0.92
     Stockholm
    0.90
    holm
    0.86
     Swedish
    0.86
    ä
    0.85
    Activations Density 0.011%

    No Known Activations