© 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. 0-RES-JB
    11. 8187
    Prev
    Next
    INDEX
    Explanations

    references to the concept of God

    oai_token-act-pair · gpt-3.5-turbo

    references to God and divine authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.72
     caf
    -0.70
    profile
    -0.68
    irements
    -0.66
    MX
    -0.65
    ocial
    -0.64
     AFL
    -0.63
    cases
    -0.63
    ISE
    -0.63
    ARS
    -0.62
    POSITIVE LOGITS
     God
    3.53
    God
    2.94
     GOD
    2.49
     god
    2.36
    god
    2.14
     Gods
    2.03
     Allah
    2.03
     deity
    1.91
     Almighty
    1.90
     Jesus
    1.81
    Activations Density 0.033%

    No Known Activations