Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 19559
    Prev
    Next
    INDEX
    Explanations

    proper names related to a specific individual named Mario

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Mario" and associated characters like "Luigi"

    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
    ORE
    -0.76
    ivities
    -0.74
    aylor
    -0.74
    ribune
    -0.73
    ynski
    -0.69
    oning
    -0.68
    angers
    -0.68
    ij士
    -0.67
    oring
    -0.67
     warrants
    -0.66
    POSITIVE LOGITS
     Kart
    1.27
     Luigi
    1.08
     Mario
    1.06
    Mario
    0.93
     Bros
    0.89
     Cuomo
    0.86
    Maker
    0.84
     Maker
    0.83
     Yoshi
    0.78
     Wii
    0.77
    Activations Density 0.008%

    No Known Activations