© 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. 3343
    Prev
    Next
    INDEX
    Explanations

    references to sports events or activities taking place at home venues

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "home" in various contexts related to sports events

    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
    ascript
    -0.75
    enegger
    -0.75
    olini
    -0.73
    uality
    -0.73
    ifter
    -0.72
    Files
    -0.71
    asus
    -0.68
    ourgeois
    -0.66
    Compan
    -0.64
     Mayer
    -0.64
    POSITIVE LOGITS
     games
    0.90
     opener
    0.88
    grown
    0.87
    coming
    0.87
     rink
    0.86
     playoff
    0.85
     teammate
    0.82
    comings
    0.81
     turf
    0.79
     stadium
    0.78
    Activations Density 0.034%

    No Known Activations