© 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. 2766
    Prev
    Next
    INDEX
    Explanations

    references to items or actions related to tracking lap times or laps in a race or competition

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lap" and its variations

    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
     Flavoring
    -0.85
    ========
    -0.65
    Premium
    -0.62
    NESS
    -0.62
    displayText
    -0.61
    xual
    -0.61
     Fargo
    -0.61
     Tob
    -0.60
    ALLY
    -0.60
     BIG
    -0.59
    POSITIVE LOGITS
    ocobo
    0.96
    dog
    0.95
    dogs
    0.93
    robe
    0.87
    ucha
    0.85
    alm
    0.83
    iths
    0.82
    els
    0.78
    icularly
    0.78
    olit
    0.78
    Activations Density 0.074%

    No Known Activations