© 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. 3-RES-JB
    11. 22924
    Prev
    Next
    INDEX
    Explanations

    mentions of clothing items, particularly skirts and hijabs

    oai_token-act-pair · gpt-3.5-turbo

    references to skirts and related clothing terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cause
    -0.72
    upon
    -0.69
    ertain
    -0.68
     pts
    -0.68
     prog
    -0.67
    eral
    -0.66
    oxicity
    -0.65
    Users
    -0.64
    KNOWN
    -0.63
    actic
    -0.63
    POSITIVE LOGITS
     skirts
    1.37
     skirt
    1.14
    cloth
    0.82
     Boots
    0.81
     Rack
    0.78
    skirts
    0.78
    cliffe
    0.78
     panties
    0.78
     Dress
    0.78
     dresses
    0.76
    Activations Density 0.008%

    No Known Activations