© 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. 9-RES-JB
    11. 1902
    Prev
    Next
    INDEX
    Explanations

    terms related to football and sports in general

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of football and related sports activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ħĭ
    -0.69
    lishes
    -0.68
    shapeshifter
    -0.65
    cule
    -0.63
    ainer
    -0.63
    ¿½
    -0.62
    Shift
    -0.62
     Rate
    -0.61
     Macro
    -0.61
    ahime
    -0.61
    POSITIVE LOGITS
     stadiums
    1.17
     soccer
    1.15
     baseball
    1.10
     football
    1.07
     basketball
    1.07
     hockey
    1.06
     stadium
    1.04
     jerseys
    0.96
     rugby
    0.94
     sports
    0.94
    Activations Density 0.367%

    No Known Activations