© 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. 11-RES-JB
    11. 20559
    Prev
    Next
    INDEX
    Explanations

    mentions of the media company ESPN, particularly in relation to sports

    oai_token-act-pair · gpt-3.5-turbo

    references to ESPN and its related content

    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
    ĸļ
    -0.80
    spection
    -0.77
    ktop
    -0.73
    abiding
    -0.71
    byn
    -0.70
    mits
    -0.70
     provoking
    -0.69
     pleading
    -0.67
    gie
    -0.67
     vain
    -0.65
    POSITIVE LOGITS
    Boston
    1.15
    Los
    1.05
     Stats
    1.05
    Chicago
    1.00
    Sports
    0.91
     Films
    0.91
     Insider
    0.89
    EW
    0.88
    Stats
    0.87
    U
    0.87
    Activations Density 0.029%

    No Known Activations