© 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. 6-RES-JB
    11. 14643
    Prev
    Next
    INDEX
    Explanations

    religious texts and related terms, particularly focusing on references to the Bible

    oai_token-act-pair · gpt-3.5-turbo

    references to the Bible and its interpretations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesota
    -0.90
     Flavoring
    -0.80
    ority
    -0.76
    ickr
    -0.75
    llular
    -0.73
    govtrack
    -0.73
    ivation
    -0.71
    "]=>
    -0.71
    ifles
    -0.69
    ials
    -0.69
    POSITIVE LOGITS
     scriptures
    0.87
     prophecy
    0.83
     translator
    0.83
     verse
    0.83
     Belt
    0.80
     transl
    0.79
     tracts
    0.78
    ñ
    0.78
     Bible
    0.78
     verses
    0.77
    Activations Density 0.015%

    No Known Activations