© 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. 1065
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of the country 'Thailand'

    oai_token-act-pair · gpt-3.5-turbo

    references to Thailand and its associated cultural aspects

    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
    ucl
    -0.83
    pring
    -0.82
     Lazarus
    -0.74
    ptive
    -0.74
    eer
    -0.73
    BAT
    -0.72
    bolt
    -0.72
    ships
    -0.71
    gage
    -0.70
    âĸ¬âĸ¬
    -0.70
    POSITIVE LOGITS
    ailand
    0.87
     Airways
    0.84
     Nguyen
    0.80
    uran
    0.78
    arma
    0.76
     clinch
    0.75
    ractor
    0.74
    ongs
    0.74
     Kong
    0.71
    nown
    0.71
    Activations Density 0.047%

    No Known Activations