© 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. 10-RES-JB
    11. 2818
    Prev
    Next
    INDEX
    Explanations

    mentions of the Catholic Church

    oai_token-act-pair · gpt-3.5-turbo

    references to the Catholic Church and its institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ript
    -0.91
    hov
    -0.90
    eters
    -0.82
    ohm
    -0.78
    nesota
    -0.77
    ilater
    -0.72
    Agent
    -0.72
    rg
    -0.71
    iven
    -0.70
    à¸
    -0.70
    POSITIVE LOGITS
     Church
    1.34
     bishops
    1.19
     priest
    1.10
     church
    1.10
     nuns
    1.08
     priests
    1.04
     clergy
    1.04
    osate
    1.03
     nun
    1.01
     Patriarch
    0.99
    Activations Density 0.033%

    No Known Activations