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. 10-RES-JB
    6. 15092
    Prev
    Next
    INDEX
    Explanations

    phrases related to "rib", such as "ribbons" or "ribeye steak"

    oai_token-act-pair · gpt-3.5-turbo

    references to ribs or rib-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GOODMAN
    -0.77
    terday
    -0.71
     Sunny
    -0.70
     groundwater
    -0.68
    NESS
    -0.62
     Grail
    -0.61
     Loan
    -0.61
    chool
    -0.61
    ĨĴ
    -0.60
     SOS
    -0.59
    POSITIVE LOGITS
    bons
    1.70
    bing
    1.07
    bon
    1.03
    ald
    0.99
    bed
    0.99
    ilant
    0.96
    bard
    0.93
    tree
    0.93
    otics
    0.90
    yrinth
    0.90
    Activations Density 0.034%

    No Known Activations