© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 15482
    Prev
    Next
    INDEX
    Explanations

    references to specific chapters or elements from religious texts, particularly related to the book of Genesis

    oai_token-act-pair · gpt-3.5-turbo

    references to the book of Genesis in the Bible

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

    No Comments

    Negative Logits
    olulu
    -1.03
    graduate
    -0.81
    legged
    -0.73
    esty
    -0.69
    amina
    -0.69
    alties
    -0.66
    ratulations
    -0.65
    ints
    -0.65
    cohol
    -0.65
    lying
    -0.65
    POSITIVE LOGITS
    esis
    1.09
     Genesis
    1.01
     Rebirth
    0.78
     Golem
    0.75
    ãĥŁ
    0.75
     Evangel
    0.72
     Exodus
    0.71
     Predator
    0.71
     Generations
    0.68
     Eve
    0.68
    Activations Density 0.015%

    No Known Activations