© 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. 10492
    Prev
    Next
    INDEX
    Explanations

    mentions of churches

    oai_token-act-pair · gpt-3.5-turbo

    references to churches

    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
     neurot
    -0.68
    DonaldTrump
    -0.67
     Haf
    -0.66
     Yak
    -0.66
    à¸
    -0.66
    LER
    -0.61
     Rog
    -0.61
     Bagg
    -0.60
    berman
    -0.60
    nir
    -0.60
    POSITIVE LOGITS
    goers
    1.18
    yard
    1.10
    esan
    1.00
    yards
    0.90
    church
    0.90
     choir
    0.88
     fathers
    0.87
     congregation
    0.86
     cha
    0.85
     church
    0.81
    Activations Density 0.019%

    No Known Activations