© 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. 7-RES-JB
    11. 19321
    Prev
    Next
    INDEX
    Explanations

    references related to sports officials, especially referees

    oai_token-act-pair · gpt-3.5-turbo

    terms related 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 @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DonaldTrump
    -0.77
    izoph
    -0.75
    igslist
    -0.72
    ocobo
    -0.71
    tom
    -0.71
    stem
    -0.70
    FINEST
    -0.67
    temp
    -0.66
     Flavoring
    -0.66
    yles
    -0.66
    POSITIVE LOGITS
     referees
    1.20
     referee
    1.16
    eree
    1.01
     offic
    0.82
     rigged
    0.82
    keepers
    0.81
    iating
    0.80
     announ
    0.79
     stopp
    0.77
     announcer
    0.77
    Activations Density 0.064%

    No Known Activations