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. 9272
    Prev
    Next
    INDEX
    Explanations

    mentions of people named Karen

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Karen."

    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
     stat
    -0.80
    rack
    -0.79
    Stat
    -0.77
     jewels
    -0.76
    stat
    -0.72
     leagues
    -0.72
    alt
    -0.69
     crypto
    -0.68
     dat
    -0.68
    stone
    -0.66
    POSITIVE LOGITS
     Karen
    3.61
     Deborah
    1.60
     Karin
    1.54
     Kathy
    1.53
     Cheryl
    1.47
     Katherine
    1.44
     Paula
    1.42
     Wendy
    1.41
     Jennifer
    1.40
     Lori
    1.40
    Activations Density 0.019%

    No Known Activations