© 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 EvalsExportsinterp-engineNEWAPI 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. 11249
    Prev
    Next
    INDEX
    Explanations

    terms related to sports officiating, particularly focusing on the role of referees

    oai_token-act-pair · gpt-3.5-turbo

    references to referees and officiating in sports

    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
    igslist
    -0.78
    izoph
    -0.73
    urat
    -0.72
    tom
    -0.71
    ssh
    -0.70
    FINEST
    -0.70
     suscept
    -0.69
     Sinai
    -0.68
    pir
    -0.68
    stem
    -0.65
    POSITIVE LOGITS
     referee
    1.12
    eree
    1.09
     referees
    1.08
     replay
    0.87
     offic
    0.83
     rigged
    0.83
     stopp
    0.82
    keeper
    0.79
    keepers
    0.78
    plays
    0.78
    Activations Density 0.123%

    No Known Activations