© 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. 7-RES-JB
    11. 24089
    Prev
    Next
    INDEX
    Explanations

    references to marathon-related events or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to marathons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    metics
    -0.82
    ongyang
    -0.69
     Aires
    -0.69
    otle
    -0.69
    obyl
    -0.68
    orum
    -0.68
    unin
    -0.66
    choes
    -0.66
    onom
    -0.65
    sheet
    -0.64
    POSITIVE LOGITS
     runner
    1.04
     runners
    0.88
     Runner
    0.86
     marathon
    0.83
     bombing
    0.82
     bombings
    0.81
    athon
    0.77
     Marathon
    0.73
    NING
    0.71
     bombers
    0.70
    Activations Density 0.033%

    No Known Activations