© 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. 20588
    Prev
    Next
    INDEX
    Explanations

    information related to large structures and venues like offices, buildings, and stadiums

    oai_token-act-pair · gpt-3.5-turbo

    details related to structural specifications and features of buildings or stadiums

    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
     nep
    -0.75
    Task
    -0.74
     undone
    -0.73
    heit
    -0.73
    gui
    -0.73
    ebin
    -0.73
    nom
    -0.72
     whistlebl
    -0.72
    step
    -0.72
    rend
    -0.71
    POSITIVE LOGITS
     stadiums
    1.98
     stadium
    1.91
     Stadium
    1.73
     ballpark
    1.50
    adium
    1.48
     Coliseum
    1.39
     arenas
    1.35
     MLB
    1.30
     arena
    1.30
     soccer
    1.29
    Activations Density 0.503%

    No Known Activations