© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 5281
    Prev
    Next
    INDEX
    Explanations

    words related to marathons

    oai_token-act-pair · gpt-3.5-turbo

    references and mentions of the Boston Marathon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orum
    -0.79
    tics
    -0.77
    under
    -0.70
    oshop
    -0.67
    tical
    -0.66
    erie
    -0.66
    olia
    -0.65
     suscept
    -0.64
    laus
    -0.63
    spr
    -0.62
    POSITIVE LOGITS
     runner
    1.08
     marathon
    1.02
     Runner
    0.95
     Marathon
    0.92
     runners
    0.90
    athon
    0.82
     Polo
    0.82
    NING
    0.78
     bombing
    0.76
    halla
    0.74
    Activations Density 0.010%

    No Known Activations