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. 1-RES-JB
    6. 8280
    Prev
    Next
    INDEX
    Explanations

    phrases related to the book of Genesis

    oai_token-act-pair · gpt-3.5-turbo

    references to the biblical book of Genesis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olulu
    -0.97
    graduate
    -0.81
    tyard
    -0.74
    orney
    -0.74
    enegger
    -0.73
    cific
    -0.73
    acca
    -0.73
    uggage
    -0.72
    asin
    -0.71
     tradem
    -0.71
    POSITIVE LOGITS
     Genesis
    1.29
    esis
    1.19
     Exodus
    0.94
     Golem
    0.80
     Classics
    0.75
     Seed
    0.73
     Kirin
    0.70
     Generations
    0.69
     Centauri
    0.69
     Generation
    0.68
    Activations Density 0.015%

    No Known Activations