© 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. 6-RES-JB
    11. 1033
    Prev
    Next
    INDEX
    Explanations

    phrases related to makeup and cosmetics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "make-up" or "composition."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ":["
    -0.68
     horizont
    -0.66
     setbacks
    -0.64
    hov
    -0.59
     liability
    -0.59
    externalActionCode
    -0.58
     seekers
    -0.58
    SPONSORED
    -0.58
    bda
    -0.57
    ibaba
    -0.57
    POSITIVE LOGITS
    Wan
    0.80
    sense
    0.69
     impression
    0.69
    minecraft
    0.69
     abundantly
    0.68
     mistake
    0.66
    ument
    0.64
    undo
    0.62
    Ò
    0.62
     determin
    0.62
    Activations Density 0.178%

    No Known Activations