© 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. 6-RES-JB
    11. 12795
    Prev
    Next
    INDEX
    Explanations

    words related to the role of a referee in sports

    oai_token-act-pair · gpt-3.5-turbo

    terms related to referees and umpiring in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocobo
    -0.75
    DonaldTrump
    -0.73
    izoph
    -0.69
    gow
    -0.69
    tom
    -0.68
    Sea
    -0.67
     Flavoring
    -0.66
    CHO
    -0.66
    stem
    -0.65
    VILLE
    -0.64
    POSITIVE LOGITS
     referees
    0.99
    eree
    0.94
     referee
    0.93
    esses
    0.86
     rigged
    0.82
    keepers
    0.74
    itatively
    0.72
    inkle
    0.71
     offic
    0.70
     arbit
    0.69
    Activations Density 0.046%

    No Known Activations