© 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. 11-RES-JB
    11. 6433
    Prev
    Next
    INDEX
    Explanations

    descriptions related to athletic abilities and skills

    oai_token-act-pair · gpt-3.5-turbo

    attributes of athletic ability and skills in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Journals
    -0.71
     boycott
    -0.65
    gently
    -0.63
     HTTPS
    -0.61
     PRESS
    -0.61
     excise
    -0.60
    leanor
    -0.60
     Seat
    -0.60
     postage
    -0.59
     Restaur
    -0.58
    POSITIVE LOGITS
     athlet
    1.23
     offensively
    1.06
     defensively
    0.94
     unmatched
    0.87
     versatility
    0.83
     suited
    0.83
     talent
    0.83
     scouts
    0.82
     chops
    0.81
     coupled
    0.80
    Activations Density 0.179%

    No Known Activations