© 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. 1-RES-JB
    11. 3191
    Prev
    Next
    INDEX
    Explanations

    references to religious figures, specifically focusing on Jesus 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 @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾
    -0.89
    ULL
    -0.79
    orph
    -0.76
    shown
    -0.74
    RAG
    -0.72
    ANY
    -0.72
    urst
    -0.70
    ickr
    -0.70
    å§
    -0.69
    ariat
    -0.67
    POSITIVE LOGITS
     Christ
    1.32
     Jesus
    1.18
    Jesus
    0.99
     Savior
    0.85
    inez
    0.84
    otle
    0.82
    esses
    0.80
    ocalypse
    0.79
     Tsukuyomi
    0.79
     Messiah
    0.79
    Activations Density 0.010%

    No Known Activations