Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 10290
    Prev
    Next
    INDEX
    Explanations

    cosmetic-related words, specifically focusing on makeup products and their application

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cosmetics and beauty products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REDACTED
    -0.88
    SPONSORED
    -0.85
    \\\\\\\\
    -0.78
    EH
    -0.76
    oran
    -0.75
    eming
    -0.75
     citation
    -0.74
    vernment
    -0.74
     guiActiveUn
    -0.73
    zek
    -0.72
    POSITIVE LOGITS
     mascara
    1.21
     cosmetics
    1.05
     lipstick
    1.01
     moistur
    1.01
     fragrance
    0.97
     coats
    0.96
     perfume
    0.95
     shampoo
    0.94
     panties
    0.93
     boutique
    0.93
    Activations Density 0.270%

    No Known Activations