© 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. 8-RES-JB
    11. 4584
    Prev
    Next
    INDEX
    Explanations

    mentions of the Orthodox community and related topics such as teachings, institutions, and leaders

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Orthodox Christianity and its related concepts or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enance
    -0.84
    nels
    -0.78
    ĸļ
    -0.77
    ptives
    -0.75
    ptoms
    -0.75
    aneously
    -0.73
    rill
    -0.72
     Keane
    -0.71
    adium
    -0.69
    arcity
    -0.68
    POSITIVE LOGITS
     Judaism
    0.94
    y
    0.92
     rabb
    0.88
     Patriarch
    0.88
    thodox
    0.86
     Jewish
    0.86
    omy
    0.85
     Church
    0.82
     affili
    0.80
     Jews
    0.79
    Activations Density 0.032%

    No Known Activations