© 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. 11-RES-JB
    11. 12506
    Prev
    Next
    INDEX
    Explanations

    information related to skincare and beauty products

    oai_token-act-pair · gpt-3.5-turbo

    content related to cosmetics and skincare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fork
    -0.85
    pend
    -0.81
    church
    -0.74
     Sutherland
    -0.74
    trak
    -0.74
     chess
    -0.74
     crane
    -0.72
     seism
    -0.72
    axe
    -0.72
     Robotics
    -0.71
    POSITIVE LOGITS
     moistur
    1.55
     sunscreen
    1.49
     acne
    1.37
     pores
    1.36
     mascara
    1.34
     dermat
    1.32
     pigment
    1.32
     lipstick
    1.31
     makeup
    1.30
     matte
    1.26
    Activations Density 0.277%

    No Known Activations