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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 13566
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Mario."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Mario" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aylor
    -0.85
    ynski
    -0.80
    arget
    -0.74
     Newsp
    -0.69
    ORE
    -0.69
    oring
    -0.67
    ivities
    -0.67
    ribune
    -0.67
    naire
    -0.65
     warrants
    -0.65
    POSITIVE LOGITS
     Kart
    1.36
     Luigi
    1.03
     Mario
    0.94
     Bros
    0.89
    Mario
    0.89
     Cuomo
    0.84
    otti
    0.80
     Polo
    0.78
    Maker
    0.77
     Wii
    0.76
    Activations Density 0.013%

    No Known Activations