© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 6428
    Prev
    Next
    INDEX
    Explanations

    references to religious worship activities

    oai_token-act-pair · gpt-3.5-turbo

    references to worship practices and religious gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    porter
    -0.72
    NER
    -0.69
    ester
    -0.67
    20439
    -0.67
    Ctrl
    -0.66
    CS
    -0.66
    ader
    -0.66
    lag
    -0.65
     ALS
    -0.64
    encer
    -0.63
    POSITIVE LOGITS
     worship
    3.94
     worsh
    2.91
     worshipped
    2.56
     vener
    2.00
     reverence
    1.67
     wors
    1.57
     reve
    1.50
     prayer
    1.43
     deities
    1.37
     congreg
    1.34
    Activations Density 0.021%

    No Known Activations