© 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. 8-RES-JB
    11. 7039
    Prev
    Next
    INDEX
    Explanations

    references to the Vatican

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Vatican

    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
    Ô
    -0.87
    Haw
    -0.79
    hirt
    -0.75
    à¸
    -0.74
    ãģ¦
    -0.74
    lasses
    -0.74
    metry
    -0.73
    isode
    -0.71
    utenant
    -0.70
    м
    -0.69
    POSITIVE LOGITS
    arium
    0.95
     Vatican
    0.88
    Leaks
    0.82
     Patriarch
    0.82
     Embassy
    0.79
    atican
    0.78
     City
    0.78
     hierarchy
    0.75
     embassy
    0.72
     Bulletin
    0.72
    Activations Density 0.028%

    No Known Activations