© 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. 8-RES-JB
    11. 24295
    Prev
    Next
    INDEX
    Explanations

    references to the word "lap", which could refer to a variety of contexts including a physical lap, a racing lap, or laps in memory

    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 @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.96
    ãĥ¼ãĥĨãĤ£
    -0.75
    xual
    -0.72
    hips
    -0.72
    merce
    -0.70
     Fargo
    -0.69
     Marketable
    -0.68
    NESS
    -0.68
    hood
    -0.66
    é¾įå¥ij士
    -0.66
    POSITIVE LOGITS
    dogs
    1.05
    ocobo
    1.02
    dog
    0.99
    ipop
    0.98
    olit
    0.89
    alm
    0.88
    robe
    0.85
    alos
    0.84
    apan
    0.83
    ois
    0.82
    Activations Density 0.037%

    No Known Activations