© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 4206
    Prev
    Next
    INDEX
    Explanations

    phrases related to religious beliefs and teachings

    oai_token-act-pair · gpt-3.5-turbo

    references to religious or spiritual themes and concepts, particularly those related to salvation and divine promises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ffield
    -0.75
    leneck
    -0.75
     runway
    -0.73
    ulton
    -0.72
     Runner
    -0.71
     interns
    -0.71
     curves
    -0.71
    emouth
    -0.71
     batted
    -0.71
    assetsadobe
    -0.70
    POSITIVE LOGITS
     scripture
    1.65
     Scripture
    1.60
     Apostle
    1.49
     scriptures
    1.48
     prayer
    1.44
     Quran
    1.42
     Jesus
    1.42
     sacrament
    1.42
     Scriptures
    1.41
     Apostles
    1.41
    Activations Density 1.105%

    No Known Activations