© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 21340
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Catholic" in the text

    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 @ 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
    rg
    -0.92
    ript
    -0.88
    gered
    -0.84
    obbies
    -0.81
    à¸
    -0.80
    eters
    -0.79
    ickr
    -0.76
    ihad
    -0.73
    */(
    -0.73
     Flavoring
    -0.73
    POSITIVE LOGITS
     Catholic
    1.00
     Church
    0.99
     Catholics
    0.97
     priests
    0.94
     priest
    0.93
     nuns
    0.92
     bishops
    0.92
     nun
    0.92
     saints
    0.90
     communion
    0.88
    Activations Density 0.009%

    No Known Activations