© 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. 14576
    Prev
    Next
    INDEX
    Explanations

    phrases containing religious references and blessings

    oai_token-act-pair · gpt-3.5-turbo

    references to divine concepts and appeals for divine intervention or blessings

    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
    anwhile
    -0.85
    Downloadha
    -0.82
    abus
    -0.79
    alore
    -0.77
    outh
    -0.73
    addle
    -0.73
    essional
    -0.73
    pole
    -0.70
    icip
    -0.70
    cheon
    -0.70
    POSITIVE LOGITS
     Almighty
    1.06
     Metatron
    0.96
     holiest
    0.91
     bless
    0.86
     persecut
    0.85
     afterlife
    0.82
     angels
    0.82
     Apostle
    0.80
     Buddha
    0.79
     Okawaru
    0.78
    Activations Density 0.217%

    No Known Activations