© 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. 5367
    Prev
    Next
    INDEX
    Explanations

    phrases related to the action of wearing or being worn

    oai_token-act-pair · gpt-3.5-turbo

    terms related to clothing or items that are worn

    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
    akespeare
    -0.84
    aminer
    -0.79
    akespe
    -0.74
    raction
    -0.72
    yrinth
    -0.72
    rase
    -0.69
    racted
    -0.69
    heid
    -0.69
    hra
    -0.68
    llor
    -0.67
    POSITIVE LOGITS
    ables
    1.11
     apparel
    1.09
     jeans
    1.07
     worn
    1.05
     clothing
    0.99
     underwear
    0.96
     gloves
    0.95
     diapers
    0.94
    wear
    0.93
     denim
    0.93
    Activations Density 0.058%

    No Known Activations