© 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. 10-RES-JB
    11. 2922
    Prev
    Next
    INDEX
    Explanations

    words related to awards and ceremonies, particularly the "Academy."

    oai_token-act-pair · gpt-3.5-turbo

    references to the Academy Awards and related organizations or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ppings
    -0.81
    sheet
    -0.73
     Bundy
    -0.73
    theless
    -0.71
    pd
    -0.70
    nir
    -0.69
    PF
    -0.68
     Malone
    -0.66
    TPS
    -0.65
    driver
    -0.65
    POSITIVE LOGITS
     Awards
    1.15
    emies
    1.08
     Award
    0.94
     graduates
    0.86
     Ruins
    0.85
     curriculum
    0.83
     graduation
    0.81
    uates
    0.78
     curric
    0.77
     academy
    0.74
    Activations Density 0.018%

    No Known Activations