© 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. 1-RES-JB
    11. 3927
    Prev
    Next
    INDEX
    Explanations

    references to specific names or terms related to Sikhism

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Sikhs" and references to the Sikh community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.83
    furt
    -0.74
    iard
    -0.72
    flies
    -0.71
    emis
    -0.71
    ball
    -0.68
    ei
    -0.68
    iology
    -0.68
     Blossom
    -0.67
    vol
    -0.66
    POSITIVE LOGITS
     Sik
    1.10
    istani
    0.95
     Guru
    0.88
     crore
    0.80
     Sikh
    0.79
    kson
    0.78
    lasses
    0.76
    yrim
    0.75
    indal
    0.74
    istan
    0.73
    Activations Density 0.007%

    No Known Activations