© 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. 4-RES-JB
    11. 2714
    Prev
    Next
    INDEX
    Explanations

    terms related to the fashion industry

    oai_token-act-pair · gpt-3.5-turbo

    terms and references related to fashion and style

    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
     moderator
    -0.77
    terness
    -0.74
    itored
    -0.71
     witness
    -0.69
    itial
    -0.69
     draining
    -0.68
    ounty
    -0.67
    aptic
    -0.67
     seeded
    -0.67
    REDACTED
    -0.66
    POSITIVE LOGITS
     boutique
    1.19
     apparel
    1.14
     Fashion
    1.13
     footwear
    1.12
     clothing
    1.10
    wear
    1.09
    fashion
    1.09
     brands
    0.99
     accessories
    0.98
     attire
    0.97
    Activations Density 0.072%

    No Known Activations