© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10987
    Prev
    Next
    INDEX
    Explanations

    items of clothing and makeup-related words

    oai_token-act-pair · gpt-3.5-turbo

    items and descriptions related to cosmetic and fashion products

    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
    SPONSORED
    -0.90
    REDACTED
    -0.87
    Unix
    -0.85
    =-=-=-=-
    -0.82
    ewitness
    -0.81
     Missions
    -0.79
    \\\\\\\\
    -0.76
    EH
    -0.74
     Samar
    -0.72
    eming
    -0.72
    POSITIVE LOGITS
     mascara
    1.06
     hairst
    0.98
     boutique
    0.95
     sleeves
    0.94
     panties
    0.93
     glossy
    0.93
     gown
    0.92
     accessories
    0.92
    wear
    0.92
    tones
    0.91
    Activations Density 0.382%

    No Known Activations