© 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
    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. 10126
    Prev
    Next
    INDEX
    Explanations

    words related to religious activities and practices, specifically focusing on the concept of prayer

    oai_token-act-pair · gpt-3.5-turbo

    references to prayer and related religious practices

    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
    transfer
    -0.79
    )=(
    -0.70
    efficients
    -0.69
     Clone
    -0.65
     Polo
    -0.62
    draft
    -0.62
    acid
    -0.60
    ortium
    -0.60
    cephal
    -0.59
    lasses
    -0.59
    POSITIVE LOGITS
     prayer
    1.28
     prayers
    1.27
     Prayer
    1.17
     vigil
    1.13
     praying
    1.11
     beads
    1.05
     mant
    1.02
     prayed
    1.00
     scripture
    1.00
     pray
    0.98
    Activations Density 0.047%

    No Known Activations