© 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. 10-RES-JB
    11. 17308
    Prev
    Next
    INDEX
    Explanations

    phrases related to winning or being victorious

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "won" and its variations, indicating victories in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    resa
    -0.75
     Norn
    -0.62
    hiba
    -0.60
    cens
    -0.58
     Kislyak
    -0.58
     sket
    -0.57
    rero
    -0.56
     beginnings
    -0.56
    0200
    -0.56
     squid
    -0.56
    POSITIVE LOGITS
    't
    1.03
     championships
    1.02
     convinc
    0.86
     Rookie
    0.83
     streaks
    0.81
     games
    0.81
     consecutive
    0.79
     trophies
    0.77
     titles
    0.77
    now
    0.76
    Activations Density 0.043%

    No Known Activations