© 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 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. 8-RES-JB
    11. 19295
    Prev
    Next
    INDEX
    Explanations

    words related to countries around the world

    oai_token-act-pair · gpt-3.5-turbo

    references to Hungary and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jad
    -0.89
    nesota
    -0.81
    phrine
    -0.77
    ctive
    -0.75
    cloth
    -0.75
    grading
    -0.72
    washed
    -0.72
    LEASE
    -0.71
    teen
    -0.70
    wards
    -0.69
    POSITIVE LOGITS
     Budapest
    0.94
    Hung
    0.93
    arians
    0.87
     Hungarian
    0.84
     Hungary
    0.75
     Viktor
    0.75
    owitz
    0.75
    naires
    0.74
    ICAN
    0.72
    ÃįÃį
    0.71
    Activations Density 0.054%

    No Known Activations