© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 23941
    Prev
    Next
    INDEX
    Explanations

    references to beauty standards and beauty-related concepts

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to beauty pageants and modeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umar
    -0.74
    etheless
    -0.73
    arbon
    -0.72
    ensable
    -0.72
    lethal
    -0.69
    intendo
    -0.68
    overe
    -0.67
    cosystem
    -0.65
    ETHOD
    -0.64
    wart
    -0.64
    POSITIVE LOGITS
     pageant
    1.22
     nude
    1.15
     salon
    1.10
     glam
    1.07
     actresses
    1.04
     bikini
    1.01
     Kardashian
    0.98
     queens
    0.97
     cosmetics
    0.96
    models
    0.95
    Activations Density 0.299%

    No Known Activations