© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 6914
    Prev
    Next
    INDEX
    Explanations

    descriptions or mentions of beauty

    oai_token-act-pair · gpt-3.5-turbo

    references to beauty in various contexts

    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
    о
    -0.73
    vernment
    -0.70
    ocating
    -0.64
    ends
    -0.64
    HF
    -0.63
    cells
    -0.63
    eng
    -0.63
    istant
    -0.63
    und
    -0.62
    wk
    -0.61
    POSITIVE LOGITS
     beauty
    3.69
     Beauty
    2.54
     beaut
    2.17
    beaut
    2.11
    Beaut
    2.08
     elegance
    1.73
     Beaut
    1.61
     beautiful
    1.53
     attractiveness
    1.47
     majesty
    1.45
    Activations Density 0.014%

    No Known Activations