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. 3-RES-JB
    6. 1464
    Prev
    Next
    INDEX
    Explanations

    descriptions or mentions of beauty

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of beauty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arbon
    -0.83
    hov
    -0.75
    renheit
    -0.73
    kson
    -0.72
    eded
    -0.72
    sol
    -0.66
    eding
    -0.66
    orum
    -0.66
    imov
    -0.64
    ÑĢ
    -0.64
    POSITIVE LOGITS
     pageant
    1.04
     beauty
    0.83
     queen
    0.77
     contests
    0.77
     contestant
    0.76
     Nicole
    0.71
     queens
    0.70
     salon
    0.67
     secrets
    0.64
    issance
    0.64
    Activations Density 0.009%

    No Known Activations