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. 0-RES-JB
    6. 6953
    Prev
    Next
    INDEX
    Explanations

    words related to religious activities, specifically prayer

    oai_token-act-pair · gpt-3.5-turbo

    references to prayer and religious invocations

    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
     Lys
    -0.75
    entially
    -0.72
    axy
    -0.71
     MX
    -0.71
    dro
    -0.70
    gemony
    -0.70
    Trend
    -0.69
     Maritime
    -0.69
    ports
    -0.67
    MX
    -0.67
    POSITIVE LOGITS
     prayer
    4.01
     prayers
    3.14
     Prayer
    3.08
     praying
    2.37
     pray
    2.31
     prayed
    2.28
     meditation
    1.60
     sermon
    1.47
     mosque
    1.47
     worship
    1.45
    Activations Density 0.019%

    No Known Activations