© 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. 8-RES-JB
    11. 3392
    Prev
    Next
    INDEX
    Explanations

    phrases related to soccer referees and their actions during a game

    oai_token-act-pair · gpt-3.5-turbo

    mentions of referees and officiating in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igslist
    -0.82
    izoph
    -0.78
    DonaldTrump
    -0.76
    stem
    -0.75
    FINEST
    -0.71
    yles
    -0.70
    tom
    -0.70
     Flavoring
    -0.69
    bian
    -0.66
    urat
    -0.66
    POSITIVE LOGITS
     referees
    1.09
     referee
    1.08
    eree
    1.01
     rigged
    0.87
    keepers
    0.81
     offic
    0.79
     awarding
    0.75
     rules
    0.74
    iating
    0.73
    keeper
    0.73
    Activations Density 0.084%

    No Known Activations