© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 2800
    Prev
    Next
    INDEX
    Explanations

    the surname "Harris"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Harris" in various contexts throughout the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rious
    -0.71
    zzi
    -0.66
    nces
    -0.63
     privilege
    -0.63
     Trident
    -0.62
    ging
    -0.60
     clearance
    -0.60
     dim
    -0.59
    thens
    -0.58
     Yugoslav
    -0.56
    POSITIVE LOGITS
    burg
    1.35
    abis
    1.07
    alez
    0.94
    laughter
    0.92
    mann
    0.92
    ippi
    0.92
    abee
    0.92
    acre
    0.87
    burgh
    0.84
    itic
    0.84
    Activations Density 0.030%

    No Known Activations