© 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. 2-RES-JB
    11. 1014
    Prev
    Next
    INDEX
    Explanations

    words denoting deities, specifically "gods"

    oai_token-act-pair · gpt-4-turbo

    references to gods or deities

    oai_token-act-pair · gpt-3.5-turbo

    references to deities or divine beings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McGr
    -0.83
     VIDEOS
    -0.75
    RAW
    -0.74
    CHAT
    -0.73
    Jen
    -0.71
    ulton
    -0.70
    York
    -0.65
    ocker
    -0.65
     Huntington
    -0.65
    DEP
    -0.65
    POSITIVE LOGITS
     worshipped
    0.97
    father
    0.93
     sacrific
    0.91
     goddess
    0.89
     gods
    0.88
    mother
    0.87
     worship
    0.87
    frey
    0.84
     Odin
    0.80
     god
    0.80
    Activations Density 0.015%

    No Known Activations