© 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. 11078
    Prev
    Next
    INDEX
    Explanations

    references to the character Mario from the Super Mario video game franchise

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the character Mario from video games

    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
    oned
    -0.81
    aylor
    -0.80
    ylon
    -0.76
    marked
    -0.75
    oning
    -0.74
    esley
    -0.73
    arget
    -0.73
    ypes
    -0.73
    ening
    -0.72
    mark
    -0.71
    POSITIVE LOGITS
     Kart
    1.34
     Bros
    1.01
     Luigi
    0.93
     Wii
    0.91
     Maker
    0.85
     Golf
    0.82
     Mario
    0.80
     Cuomo
    0.79
     Tennis
    0.78
     Drag
    0.77
    Activations Density 0.042%

    No Known Activations