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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-RES-JB
    6. 3597
    Prev
    Next
    INDEX
    Explanations

    mentions or references related to Catholicism

    oai_token-act-pair · gpt-3.5-turbo

    references to the Catholic Church

    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
    ript
    -0.93
    à¸
    -0.89
    rg
    -0.88
    gered
    -0.88
    eters
    -0.84
    ickr
    -0.76
    horn
    -0.75
    ohm
    -0.75
    inventoryQuantity
    -0.73
    nesota
    -0.73
    POSITIVE LOGITS
     nun
    0.91
     bishops
    0.90
     priest
    0.89
     nuns
    0.88
     Catholic
    0.88
     priests
    0.88
     Church
    0.87
     saints
    0.86
     communion
    0.85
     Catholics
    0.84
    Activations Density 0.010%

    No Known Activations