© 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. 11503
    Prev
    Next
    INDEX
    Explanations

    mentions of religious beliefs and practices

    oai_token-act-pair · gpt-3.5-turbo

    mentions of religious beliefs and 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
    assetsadobe
    -1.08
     Yards
    -0.88
    ĸļ
    -0.86
    éĹĺ
    -0.84
    ridor
    -0.83
     Corridor
    -0.80
     corridor
    -0.80
     Sack
    -0.79
    Layer
    -0.76
     deadlines
    -0.76
    POSITIVE LOGITS
     religions
    1.97
     religion
    1.96
     Christianity
    1.95
     atheism
    1.89
     Catholicism
    1.79
     faiths
    1.77
     religious
    1.73
     Judaism
    1.72
     relig
    1.71
     Religion
    1.66
    Activations Density 0.582%

    No Known Activations