© 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. 11-RES-JB
    11. 18486
    Prev
    Next
    INDEX
    Explanations

    mentions of winners or determining a winner in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to a winner or winning outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uli
    -0.70
    reon
    -0.64
    rients
    -0.64
     sulf
    -0.64
    otrop
    -0.61
    Ku
    -0.61
    ohyd
    -0.60
    rient
    -0.59
    aligned
    -0.59
     Authorization
    -0.59
    POSITIVE LOGITS
     winner
    1.03
     winners
    0.98
     contestant
    0.91
     prizes
    0.85
     Winner
    0.83
     bidder
    0.80
     Winners
    0.78
    Winner
    0.78
     loser
    0.77
    liness
    0.76
    Activations Density 0.053%

    No Known Activations