© 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. 10717
    Prev
    Next
    INDEX
    Explanations

    references to the racing sport Formula 1

    oai_token-act-pair · gpt-3.5-turbo

    references to Formula 1 racing

    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
    bery
    -0.78
    pex
    -0.74
    abee
    -0.72
    rand
    -0.71
     Rudolph
    -0.67
     MacArthur
    -0.65
     Pru
    -0.65
    ãĥł
    -0.64
    AGES
    -0.63
    peror
    -0.61
    POSITIVE LOGITS
     betting
    0.98
     stadiums
    0.93
     enthusiasts
    0.92
     fandom
    0.92
     leagues
    0.91
     clubs
    0.91
     Players
    0.89
     viewership
    0.88
     competitions
    0.88
     Clubs
    0.87
    Activations Density 0.118%

    No Known Activations