Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 20993
    Prev
    Next
    INDEX
    Explanations

    phrases related to clothing items and accessories

    oai_token-act-pair · gpt-3.5-turbo

    references to clothing and wardrobe items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cann
    -0.69
     compounds
    -0.68
    asta
    -0.67
    aster
    -0.67
     tort
    -0.66
     Hug
    -0.64
     craw
    -0.64
    pite
    -0.64
     vapor
    -0.63
    ooks
    -0.62
    POSITIVE LOGITS
     wardrobe
    3.30
     flock
    1.28
    uria
    1.02
    vre
    0.94
     Olivia
    0.91
    MU
    0.89
    robe
    0.87
    folios
    0.86
     tailor
    0.85
     rollout
    0.83
    Activations Density 0.033%

    No Known Activations