© 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. 8243
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names of individuals, especially those with the surname "Singh"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Singh" 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
    phis
    -0.83
    bidden
    -0.77
    olitan
    -0.74
    placed
    -0.73
    aredevil
    -0.70
    ometimes
    -0.68
    ascript
    -0.68
    inarily
    -0.67
    melon
    -0.67
    izons
    -0.66
    POSITIVE LOGITS
     Yad
    1.24
     Singh
    1.03
     Chau
    1.03
     Sharma
    0.99
     Chou
    0.94
     Sabha
    0.94
     Dh
    0.93
     Gupta
    0.92
     Bh
    0.91
     Patel
    0.90
    Activations Density 0.036%

    No Known Activations