© 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. 8-RES-JB
    11. 6342
    Prev
    Next
    INDEX
    Explanations

    keywords related to display styles and programming code structures

    oai_token-act-pair · gpt-3.5-turbo

    instances of display-related terms in programming contexts

    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
    owsky
    -0.80
    uddin
    -0.76
    istani
    -0.74
    pei
    -0.73
    externalActionCode
    -0.71
    lez
    -0.68
    apeake
    -0.67
    economic
    -0.66
    laus
    -0.64
    unin
    -0.64
    POSITIVE LOGITS
     Thumbnails
    0.94
    Pixel
    0.86
    igators
    0.84
     prominently
    0.83
     displays
    0.81
    display
    0.81
     display
    0.81
    istics
    0.79
     banners
    0.75
    holders
    0.75
    Activations Density 0.041%

    No Known Activations