© 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. 3365
    Prev
    Next
    INDEX
    Explanations

    references to religious texts and beliefs

    oai_token-act-pair · gpt-3.5-turbo

    expressions of divine power and authority in religious contexts

    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
     Chilean
    -0.91
     Poland
    -0.76
    Pol
    -0.75
     Carnegie
    -0.74
     Chile
    -0.74
    Columb
    -0.73
    uca
    -0.73
     Buenos
    -0.73
     Canter
    -0.73
     Ukrain
    -0.72
    POSITIVE LOGITS
     Allaah
    1.92
     Allah
    1.51
    Allah
    1.45
     Ibn
    1.36
     Imam
    1.33
     Qur
    1.30
     Shay
    1.28
     Muhammad
    1.24
     Abu
    1.23
     Quran
    1.23
    Activations Density 0.122%

    No Known Activations