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. 12564
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically names with the term "Jean"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Jean."

    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
    TPPStreamerBot
    -0.80
    ãĥ¼ãĥ³
    -0.80
    awar
    -0.71
    ramid
    -0.69
    earable
    -0.68
     Flavoring
    -0.68
    Ö¼
    -0.68
    holders
    -0.68
    BIP
    -0.67
    meg
    -0.66
    POSITIVE LOGITS
    ette
    0.96
     Francois
    0.86
     Claude
    0.86
     Jean
    0.84
     Jacques
    0.81
     François
    0.80
     Baptist
    0.77
     Pierre
    0.76
    esis
    0.76
    Cla
    0.75
    Activations Density 0.015%

    No Known Activations