© 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. 0-RES-JB
    11. 1158
    Prev
    Next
    INDEX
    Explanations

    phrases related to religious contexts, particularly with the word "Holy"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Holy," particularly in conjunction with religious or historical contexts

    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
    kamp
    -0.76
     escal
    -0.67
     conve
    -0.64
     tox
    -0.64
    witz
    -0.63
    edes
    -0.62
     automation
    -0.62
    tackle
    -0.62
    ported
    -0.61
    arant
    -0.61
    POSITIVE LOGITS
     Holy
    3.82
    Holy
    2.89
     holy
    2.19
    holy
    2.12
     Sacred
    1.53
     holiest
    1.47
     Vatican
    1.44
     Sacrament
    1.39
     Divine
    1.39
     Blessed
    1.29
    Activations Density 0.009%

    No Known Activations