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. 4-RES-JB
    6. 3445
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically the name "Lyn"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Lyn" and related derivatives, indicating a focus on a specific individual

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

    No Comments

    Negative Logits
    pmwiki
    -0.80
    displayText
    -0.76
    orage
    -0.72
     containment
    -0.71
     Crimean
    -0.69
    âĶģ
    -0.67
    NRS
    -0.66
     Pradesh
    -0.64
    aternity
    -0.63
     Immunity
    -0.62
    POSITIVE LOGITS
     Lyn
    1.17
    sey
    1.04
    Lyn
    0.91
    ette
    0.90
    nette
    0.83
    seys
    0.82
     Crow
    0.81
    elong
    0.80
     Ping
    0.77
    cus
    0.77
    Activations Density 0.004%

    No Known Activations