© 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. 10-RES-JB
    11. 2985
    Prev
    Next
    INDEX
    Explanations

    mentions of religious figures, especially popes and their activities

    oai_token-act-pair · gpt-3.5-turbo

    references to different Popes and the Vatican

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ript
    -0.80
    nesota
    -0.79
    selves
    -0.71
     Brawl
    -0.69
     Wonderland
    -0.69
    ÑĮ
    -0.67
    uld
    -0.66
    aze
    -0.65
    mental
    -0.64
    hooting
    -0.64
    POSITIVE LOGITS
     Francis
    1.37
     Benedict
    1.18
    Franc
    0.94
    Pope
    0.91
     XVI
    0.89
     Pope
    0.88
     pont
    0.87
     pope
    0.86
     Clement
    0.84
     Archbishop
    0.83
    Activations Density 0.025%

    No Known Activations