© 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. 9-RES-JB
    11. 14765
    Prev
    Next
    INDEX
    Explanations

    references to places of worship, specifically temples

    oai_token-act-pair · gpt-3.5-turbo

    references to places or structures associated with the term "temple."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iability
    -0.76
    nesota
    -0.70
    imil
    -0.69
    leneck
    -0.68
    ÑĮ
    -0.67
    agher
    -0.67
    Consumer
    -0.64
    ives
    -0.64
    20439
    -0.64
    enegger
    -0.63
    POSITIVE LOGITS
     ceremonies
    0.92
     temple
    0.87
     rites
    0.82
     temples
    0.79
     ceremony
    0.79
    plates
    0.78
     procession
    0.77
     bells
    0.75
    inence
    0.75
    mage
    0.74
    Activations Density 0.051%

    No Known Activations