© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6284
    Prev
    Next
    INDEX
    Explanations

    words related to the term "Win"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the brand "Win."

    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
    ãĥĥãĥī
    -0.81
    plate
    -0.70
     underground
    -0.69
    plates
    -0.67
     hemisphere
    -0.67
    FORE
    -0.66
    heading
    -0.64
    isode
    -0.64
    911
    -0.64
    acas
    -0.64
    POSITIVE LOGITS
     Win
    3.71
    Win
    2.43
     WIN
    1.97
     Wins
    1.91
    win
    1.89
     win
    1.86
    WIN
    1.56
     Lose
    1.49
     Winning
    1.36
     wins
    1.31
    Activations Density 0.014%

    No Known Activations