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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 2203
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mario" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Mario" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aylor
    -0.95
    arget
    -0.77
    ynski
    -0.75
    oring
    -0.75
    ORE
    -0.74
    umbnails
    -0.73
    esley
    -0.73
    oned
    -0.73
    Ö¼
    -0.72
    ypes
    -0.71
    POSITIVE LOGITS
     Kart
    1.25
     Luigi
    0.92
     Polo
    0.87
     Maker
    0.85
     Cuomo
    0.84
     Bros
    0.83
     Mario
    0.77
     Drag
    0.76
    Maker
    0.72
     Pok
    0.70
    Activations Density 0.031%

    No Known Activations