© 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. 9-RES-JB
    11. 10113
    Prev
    Next
    INDEX
    Explanations

    phrases related to putting clothes or accessories on

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the action of "putting on" or wearing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.72
    yll
    -0.63
    ESA
    -0.63
     Distribution
    -0.62
    hower
    -0.60
     SOU
    -0.59
    rior
    -0.59
    ~~~~~~~~
    -0.59
    ELF
    -0.57
    emetery
    -0.56
    POSITIVE LOGITS
     airs
    0.93
    erous
    0.86
     tremend
    0.84
    Downloadha
    0.84
    shirts
    0.78
    */(
    0.76
    unci
    0.71
    rir
    0.67
    ibaba
    0.66
    VIDIA
    0.65
    Activations Density 0.034%

    No Known Activations