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. 8775
    Prev
    Next
    INDEX
    Explanations

    makeup-related terms and activities

    oai_token-act-pair · gpt-3.5-turbo

    references to makeup and related beauty products

    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
    EH
    -0.78
    coni
    -0.73
    wer
    -0.69
     Fal
    -0.69
    eph
    -0.68
    ua
    -0.66
    har
    -0.66
    £
    -0.65
    cial
    -0.64
    stadt
    -0.63
    POSITIVE LOGITS
     makeup
    3.93
     mascara
    1.66
     lipstick
    1.66
     cosmetics
    1.55
     sunscreen
    1.54
     complexion
    1.44
     perfume
    1.36
     composition
    1.27
     jewelry
    1.26
     wardrobe
    1.19
    Activations Density 0.013%

    No Known Activations