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. 0-RES-JB
    6. 8712
    Prev
    Next
    INDEX
    Explanations

    words related to a specific place or person named "Kyrie"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Ky," indicating a focus on a specific geographic or political entity, likely Kentucky

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Twain
    -0.82
     trough
    -0.70
     iPads
    -0.66
     bin
    -0.64
     ®
    -0.64
    aser
    -0.64
    iculty
    -0.64
    thood
    -0.64
    netflix
    -0.64
    peed
    -0.63
    POSITIVE LOGITS
     Ky
    3.93
    Ky
    3.35
    KY
    1.82
     KY
    1.77
     Okin
    1.33
     Kentucky
    1.30
     Lv
    1.30
     Kyoto
    1.28
     Kw
    1.25
     Ryu
    1.25
    Activations Density 0.009%

    No Known Activations