© 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. 4-RES-JB
    11. 22618
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to sports clubs

    oai_token-act-pair · gpt-3.5-turbo

    instances of statistical performance metrics in sports contexts

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

    No Comments

    Negative Logits
    boro
    -0.75
     solic
    -0.73
     nonprofits
    -0.69
    hovah
    -0.68
     someday
    -0.67
     Cindy
    -0.67
    igslist
    -0.65
    awei
    -0.64
     behaviors
    -0.64
    ertodd
    -0.64
    POSITIVE LOGITS
    England
    0.93
    Scotland
    0.89
    Sport
    0.89
    Liverpool
    0.86
    iverpool
    0.85
     Premiership
    0.82
    Arsenal
    0.81
     centre
    0.78
    Players
    0.78
     Leicester
    0.78
    Activations Density 0.307%

    No Known Activations