© 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. 0-RES-JB
    11. 12566
    Prev
    Next
    INDEX
    Explanations

    words related to competitions or competitive events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of competitive events or contests, particularly races

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fired
    -0.67
    Det
    -0.67
     warrant
    -0.67
    cess
    -0.65
     Pav
    -0.63
    det
    -0.62
    æĸ¹
    -0.62
     Prov
    -0.61
    ffer
    -0.61
    forward
    -0.60
    POSITIVE LOGITS
     races
    4.09
     Races
    2.95
     race
    2.47
     Race
    2.09
    Race
    2.07
    race
    1.79
     racing
    1.59
     raced
    1.50
     sexes
    1.38
     fights
    1.37
    Activations Density 0.012%

    No Known Activations