© 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. 2895
    Prev
    Next
    INDEX
    Explanations

    names related to politics and religion, specifically focusing on "Shah."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Shah" and its variations in various contexts

    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
     Wilmington
    -0.72
    oké
    -0.72
    ICE
    -0.66
    ãĤī
    -0.63
    ALLY
    -0.62
     Echo
    -0.62
     Staten
    -0.61
    ertodd
    -0.61
     Kentucky
    -0.60
     Beacon
    -0.59
    POSITIVE LOGITS
    aji
    1.04
     Alam
    1.00
     Ruk
    0.99
    zeb
    0.96
    ulk
    0.95
    istani
    0.92
    abad
    0.90
    abi
    0.88
    len
    0.88
    idi
    0.85
    Activations Density 0.030%

    No Known Activations