© 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. 0-RES-JB
    11. 15835
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the Muslim community

    oai_token-act-pair · gpt-3.5-turbo

    references to Muslims or the Muslim community

    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
    TB
    -0.73
    rost
    -0.72
     compressed
    -0.70
     coil
    -0.69
     coils
    -0.67
     Bott
    -0.67
     Stard
    -0.64
    Bott
    -0.64
    ISON
    -0.63
    oda
    -0.62
    POSITIVE LOGITS
     Muslim
    3.62
    Muslim
    3.00
     Muslims
    2.84
    Muslims
    2.60
     Islamic
    2.34
     Islam
    2.27
    Islamic
    2.20
    Islam
    2.19
     Islamist
    2.18
     mosque
    2.09
    Activations Density 0.019%

    No Known Activations