© 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. 0-RES-JB
    11. 5410
    Prev
    Next
    INDEX
    Explanations

    terms related to winning or victory

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "win" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imaru
    -0.73
    Material
    -0.71
    limits
    -0.66
    requency
    -0.64
    articles
    -0.64
    indal
    -0.63
     Mysteries
    -0.63
    papers
    -0.63
     largeDownload
    -0.62
    ellen
    -0.62
    POSITIVE LOGITS
     win
    3.60
     wins
    2.37
     victory
    2.25
     Win
    2.05
    win
    1.98
     winning
    1.95
     victories
    1.90
    Win
    1.89
     WIN
    1.83
     defeat
    1.67
    Activations Density 0.019%

    No Known Activations