© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16710
    Prev
    Next
    INDEX
    Explanations

    the name "Morgan" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Morgan."

    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
    lihood
    -0.92
    ension
    -0.69
    ract
    -0.68
    ensions
    -0.65
    Ħ¢
    -0.63
    ľ
    -0.62
    ================================================================
    -0.61
     salsa
    -0.61
    uction
    -0.60
     humble
    -0.60
    POSITIVE LOGITS
     Stanley
    0.94
     Spur
    0.90
    gage
    0.90
    dale
    0.90
     Freeman
    0.87
    igans
    0.87
    itic
    0.86
     Chase
    0.82
    tex
    0.80
    imet
    0.79
    Activations Density 0.018%

    No Known Activations