© 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. 11-RES-JB
    11. 5116
    Prev
    Next
    INDEX
    Explanations

    phrases related to Muslims and societal commentary

    oai_token-act-pair · gpt-3.5-turbo

    positive references to the Muslim community and discussions around their societal roles and challenges

    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
     Xperia
    -0.95
    Bott
    -0.86
    rolet
    -0.82
     Lys
    -0.82
     Hydro
    -0.81
     Rhod
    -0.80
     goalt
    -0.79
     CG
    -0.79
     Bott
    -0.78
     Bottle
    -0.78
    POSITIVE LOGITS
     Muslim
    2.46
     Muslims
    2.43
    Muslims
    2.42
     mosques
    2.38
     Islam
    2.37
    Muslim
    2.35
     mosque
    2.33
    Islam
    2.20
     Mosque
    2.18
     Quran
    2.14
    Activations Density 0.563%

    No Known Activations