© 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. 3-RES-JB
    11. 15189
    Prev
    Next
    INDEX
    Explanations

    expressions related to winning or being declared as the winner

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of "winner" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elsius
    -0.70
    uli
    -0.69
    estation
    -0.69
    ugu
    -0.68
    rients
    -0.68
    aeda
    -0.67
    uku
    -0.67
    abb
    -0.66
    uld
    -0.66
    MpServer
    -0.66
    POSITIVE LOGITS
     winner
    0.98
     Winner
    0.92
    Winner
    0.89
     winners
    0.82
     laureate
    0.81
     prize
    0.80
     loser
    0.76
     Hugo
    0.74
     contestant
    0.72
    athon
    0.72
    Activations Density 0.012%

    No Known Activations