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. 1-RES-JB
    6. 16696
    Prev
    Next
    INDEX
    Explanations

    names with a specific pattern, likely looking for a specific individual's name

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to specific individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    namese
    -0.87
    ertation
    -0.77
    ingly
    -0.76
    æĦ
    -0.75
     spirited
    -0.73
     thous
    -0.71
    ains
    -0.70
    ained
    -0.70
    abilia
    -0.65
    ĭ
    -0.64
    POSITIVE LOGITS
     Zig
    1.09
    zag
    1.04
    phrine
    0.95
     Zah
    0.88
    vez
    0.88
    agame
    0.87
    iggurat
    0.83
     Zin
    0.81
    ebra
    0.80
    ZZ
    0.80
    Activations Density 0.017%

    No Known Activations