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. 10917
    Prev
    Next
    INDEX
    Explanations

    names of people named Nicholas

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Nicholas."

    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
    ebook
    -0.78
    verb
    -0.77
    lance
    -0.73
    marked
    -0.72
    meaning
    -0.72
    repe
    -0.71
    front
    -0.70
    fare
    -0.70
    naire
    -0.70
    intention
    -0.69
    POSITIVE LOGITS
    olas
    1.18
     Cage
    1.01
     Nicholas
    0.92
    ettings
    0.85
    olson
    0.73
    ols
    0.72
    hift
    0.72
     Maduro
    0.72
     Krist
    0.70
     Brend
    0.69
    Activations Density 0.006%

    No Known Activations