© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 16261
    Prev
    Next
    INDEX
    Explanations

    phrases related to religion and spirituality

    oai_token-act-pair · gpt-3.5-turbo

    references to religious themes and divine attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stereotyp
    -0.75
    asel
    -0.75
    ampunk
    -0.75
    */(
    -0.75
    umpy
    -0.73
    uphem
    -0.71
     stereotypical
    -0.71
     Kazakh
    -0.71
    kees
    -0.71
     scare
    -0.69
    POSITIVE LOGITS
     Almighty
    1.24
     Savior
    1.22
     everlasting
    1.12
     Heavenly
    1.12
     Holy
    1.12
     Christ
    1.11
     Creator
    1.10
     heavenly
    1.10
     Jesus
    1.09
     Divine
    1.09
    Activations Density 0.213%

    No Known Activations