Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 13124
    Prev
    Next
    INDEX
    Explanations

    references to religious texts, particularly the Bible

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Bible and its various interpretations or usages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesota
    -0.85
    ials
    -0.80
    ickr
    -0.76
    */(
    -0.75
    "]=>
    -0.74
    ourning
    -0.73
    Ey
    -0.72
    details
    -0.70
     Flavoring
    -0.70
    ancers
    -0.69
    POSITIVE LOGITS
     Bible
    0.97
     bible
    0.92
     scriptures
    0.85
     tracts
    0.83
     patriarch
    0.83
     Scriptures
    0.82
     tract
    0.80
    iblical
    0.78
     translator
    0.78
     prophecy
    0.77
    Activations Density 0.007%

    No Known Activations