© 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. 0-RES-JB
    11. 14750
    Prev
    Next
    INDEX
    Explanations

    mentions of Switzerland or Swiss-related entities

    oai_token-act-pair · gpt-3.5-turbo

    references to Switzerland

    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
    ̶
    -0.75
    âĶĢâĶĢâĶĢâĶĢ
    -0.74
    ocations
    -0.70
    ||||
    -0.68
    addon
    -0.67
    orne
    -0.63
    ._
    -0.63
    Contents
    -0.62
    interstitial
    -0.62
    cox
    -0.62
    POSITIVE LOGITS
     Swiss
    3.83
     Switzerland
    2.38
     Zurich
    2.19
     Austrian
    1.89
     Swedish
    1.88
     Belgian
    1.83
     Argentine
    1.64
     Chilean
    1.62
     Danish
    1.61
     Finnish
    1.59
    Activations Density 0.011%

    No Known Activations