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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 23016
    Prev
    Next
    INDEX
    Explanations

    instances of mentions of makeup in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to makeup and cosmetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izen
    -0.92
    ollow
    -0.79
    inel
    -0.73
    awar
    -0.73
    imov
    -0.73
    âķIJâķIJ
    -0.73
    ighting
    -0.72
    iscopal
    -0.71
    overe
    -0.69
     Hammond
    -0.69
    POSITIVE LOGITS
     makeup
    0.95
     brushes
    0.88
    issance
    0.77
     dermat
    0.76
     artist
    0.76
    ipedia
    0.75
     artists
    0.73
     Brus
    0.72
     cosmetics
    0.71
     tutorials
    0.71
    Activations Density 0.056%

    No Known Activations