© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 13476
    Prev
    Next
    INDEX
    Explanations

    instances of beliefs or faith in religious or philosophical concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating belief or faith in various concepts, especially religious or philosophical beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Detected
    -0.74
    soever
    -0.73
    irable
    -0.73
    isky
    -0.71
    UFC
    -0.69
    QL
    -0.67
    ISON
    -0.67
    Dispatch
    -0.66
    519
    -0.66
    >>\
    -0.65
    POSITIVE LOGITS
     miracles
    1.33
     reincarn
    1.15
     ghosts
    1.02
     God
    0.96
     angels
    0.93
     unic
    0.89
     karma
    0.88
     miracle
    0.88
     miraculous
    0.87
     heaven
    0.85
    Activations Density 0.092%

    No Known Activations