© 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. 13937
    Prev
    Next
    INDEX
    Explanations

    mentions of sports draft picks and selections

    oai_token-act-pair · gpt-3.5-turbo

    references to draft picks and player selections in sports contexts

    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
     OPER
    -0.82
    wordpress
    -0.80
     intermittent
    -0.75
    Linux
    -0.75
     reconnect
    -0.74
     kW
    -0.74
    Oper
    -0.72
    ythm
    -0.72
    nect
    -0.72
     behavi
    -0.71
    POSITIVE LOGITS
     picks
    1.53
     draft
    1.53
    Draft
    1.48
     selections
    1.45
     Picks
    1.34
     Draft
    1.29
     drafting
    1.29
     lottery
    1.28
     pick
    1.26
     selection
    1.25
    Activations Density 0.305%

    No Known Activations