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. 3161
    Prev
    Next
    INDEX
    Explanations

    proper names related to the name "Kate" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Kate"

    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
    astern
    -0.84
    agn
    -0.77
     evid
    -0.71
     cob
    -0.70
     upgr
    -0.66
     FI
    -0.65
     incumb
    -0.65
    lig
    -0.64
     inhibitor
    -0.63
     underground
    -0.62
    POSITIVE LOGITS
     Kate
    3.61
    Kate
    3.28
     Kathryn
    1.82
     Katherine
    1.66
     Katie
    1.64
     Chloe
    1.62
     Catherine
    1.43
     Juliet
    1.40
    Jane
    1.38
     Zoe
    1.35
    Activations Density 0.015%

    No Known Activations