Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22327
    Prev
    Next
    INDEX
    Explanations

    references to religious figures, specifically focusing on the figure of Christ

    oai_token-act-pair · gpt-3.5-turbo

    references to Jesus Christ

    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
    uffle
    -0.66
     veto
    -0.65
    ases
    -0.65
    orter
    -0.64
    Raid
    -0.63
    uci
    -0.61
    SPA
    -0.61
    puff
    -0.60
    raf
    -0.60
    bies
    -0.60
    POSITIVE LOGITS
     Christ
    3.72
    Christ
    2.28
     CHRIST
    2.20
     Jesus
    2.03
     christ
    1.83
    Jesus
    1.78
     Messiah
    1.57
    christ
    1.57
     God
    1.54
     Christianity
    1.54
    Activations Density 0.015%

    No Known Activations