© 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. 0-RES-JB
    11. 15370
    Prev
    Next
    INDEX
    Explanations

    mentions of the Orthodox religion

    oai_token-act-pair · gpt-3.5-turbo

    references to Orthodox Christianity

    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
     tracker
    -0.78
     batted
    -0.76
    db
    -0.71
    MX
    -0.71
     java
    -0.70
     Sawyer
    -0.66
     cylinder
    -0.64
    yer
    -0.63
     db
    -0.63
    hire
    -0.61
    POSITIVE LOGITS
     Orthodox
    3.92
    thodox
    2.55
     Torah
    1.72
    orthodox
    1.71
     Patriarch
    1.69
     Episcopal
    1.64
     Judaism
    1.60
     Lutheran
    1.57
     orthodox
    1.55
     Protestant
    1.53
    Activations Density 0.027%

    No Known Activations