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. 19607
    Prev
    Next
    INDEX
    Explanations

    keywords related to the retailer "Kmart"

    oai_token-act-pair · gpt-3.5-turbo

    references to retail stores or shopping locations

    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
    ãĤ¯
    -0.73
    Appearances
    -0.72
     deposits
    -0.63
     Nieto
    -0.62
     Tiny
    -0.61
     âī¡
    -0.60
     tilt
    -0.59
     buildup
    -0.59
     Hyp
    -0.58
     Dys
    -0.58
    POSITIVE LOGITS
    mart
    4.72
     mart
    1.68
    Mart
    1.28
    swick
    1.03
    park
    1.03
     martial
    1.02
     Martial
    1.01
    mith
    0.97
    pun
    0.96
     Mart
    0.94
    Activations Density 0.008%

    No Known Activations