© 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. 4-RES-JB
    11. 10513
    Prev
    Next
    INDEX
    Explanations

    mentions of clothing or accessories

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe various items of clothing being worn by individuals

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

    No Comments

    Negative Logits
    ancock
    -0.91
     Dhabi
    -0.82
    terness
    -0.80
    agonist
    -0.78
     Fiscal
    -0.77
     Distance
    -0.75
    raq
    -0.74
    Reviewer
    -0.74
     Seeking
    -0.72
    orrow
    -0.72
    POSITIVE LOGITS
     sleeves
    0.94
     nails
    0.93
    cloth
    0.85
     parap
    0.84
     panties
    0.83
     prost
    0.83
     gloves
    0.83
     mustache
    0.83
     dolls
    0.80
     stereotypical
    0.80
    Activations Density 0.184%

    No Known Activations