© 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. 4-RES-JB
    11. 17330
    Prev
    Next
    INDEX
    Explanations

    religious terms and concepts related to Catholicism and church hierarchy

    oai_token-act-pair · gpt-3.5-turbo

    references to religious institutions and doctrines

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

    No Comments

    Negative Logits
    à¸
    -0.80
     Rail
    -0.74
    SourceFile
    -0.73
     guiName
    -0.72
     durability
    -0.71
    Pak
    -0.68
    ilage
    -0.67
    Grab
    -0.67
    hover
    -0.67
     engineered
    -0.67
    POSITIVE LOGITS
    lesiastical
    1.12
    byter
    1.11
     baptism
    1.10
     Scripture
    1.10
     bapt
    1.07
     Lutheran
    1.05
     theolog
    1.04
     XVI
    1.01
     theology
    0.99
     Benedict
    0.98
    Activations Density 0.150%

    No Known Activations