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. 11745
    Prev
    Next
    INDEX
    Explanations

    references to different units of measurement such as cups, liters, teaspoons, and quantities related to cooking

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of cups and their quantities

    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
     Pione
    -0.64
    eering
    -0.63
     rationale
    -0.63
    ggies
    -0.62
     Develop
    -0.62
     Fundamental
    -0.61
     Wildcats
    -0.61
    OLOG
    -0.61
     Bond
    -0.61
     Intellectual
    -0.61
    POSITIVE LOGITS
    cakes
    1.39
     cups
    1.33
    cup
    1.17
    cake
    1.15
    poon
    1.14
    poons
    1.07
     Cups
    0.99
     cup
    0.95
     containers
    0.84
    eries
    0.82
    Activations Density 0.003%

    No Known Activations