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. 1437
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "iPad"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Apple products, specifically the iPad

    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
    vernment
    -0.78
    olulu
    -0.76
    hov
    -0.74
    inances
    -0.73
    ovych
    -0.69
    anwhile
    -0.69
    soType
    -0.69
    vironment
    -0.68
    achusetts
    -0.67
    oney
    -0.66
    POSITIVE LOGITS
     iPad
    1.29
    Pad
    1.12
     MacBook
    1.11
     iPads
    0.96
     tablet
    0.95
     iPod
    0.92
    iPhone
    0.91
    pad
    0.90
     tablets
    0.90
     Tablet
    0.90
    Activations Density 0.004%

    No Known Activations