© 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. 10-RES-JB
    11. 7083
    Prev
    Next
    INDEX
    Explanations

    references to the Muslim community

    oai_token-act-pair · gpt-3.5-turbo

    references to the Muslim community and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angled
    -0.81
    TOP
    -0.76
    amina
    -0.74
    inventoryQuantity
    -0.70
     Vaugh
    -0.69
    ground
    -0.68
    ainer
    -0.68
    grounds
    -0.67
    anke
    -0.67
    vg
    -0.66
    POSITIVE LOGITS
     Brotherhood
    1.32
     cleric
    1.04
    istani
    1.04
    abad
    1.02
     clerics
    1.00
    majority
    0.95
     supremacist
    0.93
     fundamentalist
    0.92
    ophobic
    0.91
     pilgrims
    0.88
    Activations Density 0.036%

    No Known Activations