© 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. 1-RES-JB
    11. 20364
    Prev
    Next
    INDEX
    Explanations

    references to the physical location on a person's body known as a "lap"

    oai_token-act-pair · gpt-3.5-turbo

    the term "lap" and its variations, indicating a focus on the context of laps or measures of distance, time, or positioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.92
     Marketable
    -0.68
     unauthorized
    -0.63
    ãĥ¼ãĥĨãĤ£
    -0.63
    é¾įå¥ij士
    -0.63
     Occupy
    -0.62
     Fargo
    -0.62
    é»Ĵ
    -0.60
    SpaceEngineers
    -0.60
    merce
    -0.59
    POSITIVE LOGITS
     lap
    1.17
     Lap
    1.07
    lap
    1.00
    ipop
    0.87
    dogs
    0.87
    ocobo
    0.84
    alm
    0.80
    pit
    0.78
    iths
    0.78
    rosc
    0.76
    Activations Density 0.005%

    No Known Activations