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. 7381
    Prev
    Next
    INDEX
    Explanations

    mentions of the city Tokyo

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Tokyo."

    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
    hemy
    -0.74
    onies
    -0.73
    apple
    -0.72
    inelli
    -0.72
    theless
    -0.72
    lain
    -0.71
    lv
    -0.68
    rals
    -0.68
    ebook
    -0.68
    perse
    -0.65
    POSITIVE LOGITS
     Babel
    0.88
     Tokyo
    0.82
     Lumpur
    0.80
     Dome
    0.75
     Japan
    0.73
    amaru
    0.73
    Tok
    0.73
     Xan
    0.72
    ichi
    0.70
    iji
    0.69
    Activations Density 0.006%

    No Known Activations