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. 1-RES-JB
    6. 1523
    Prev
    Next
    INDEX
    Explanations

    terms related to food and desserts

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of desserts and pastries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aird
    -0.70
     Metropolitan
    -0.64
     Ort
    -0.63
     Mutual
    -0.63
     Levi
    -0.61
     Vest
    -0.61
    lev
    -0.61
     scanners
    -0.60
    inyl
    -0.60
     Apostle
    -0.59
    POSITIVE LOGITS
     pudding
    1.21
    cakes
    1.20
    cake
    1.19
    essert
    1.08
     desserts
    1.08
     dessert
    1.07
     cakes
    1.03
     cake
    1.00
     pastry
    0.97
     sweets
    0.94
    Activations Density 0.019%

    No Known Activations