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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-RES-JB
    6. 601
    Prev
    Next
    INDEX
    Explanations

    phrases related to numerical values or rankings

    oai_token-act-pair · gpt-3.5-turbo

    references to the numbers six, five, and four, particularly in a context related to sports or competition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    USD
    -0.72
     crawl
    -0.69
    OCK
    -0.68
    igation
    -0.67
    adel
    -0.63
    è¦ļéĨĴ
    -0.62
     clock
    -0.61
     includ
    -0.61
     DOI
    -0.61
    cd
    -0.61
    POSITIVE LOGITS
    teen
    1.43
    een
    1.05
    teenth
    0.95
     Hundred
    0.92
     Lives
    0.92
     Mile
    0.91
     Thousand
    0.86
     Hour
    0.85
     Seasons
    0.83
     Vision
    0.82
    Activations Density 0.053%

    No Known Activations