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. 9-RES-JB
    6. 12813
    Prev
    Next
    INDEX
    Explanations

    keywords related to news delivery schedules

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to news delivery and subscription services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iage
    -0.73
    escription
    -0.68
    ante
    -0.65
    urat
    -0.64
    ilion
    -0.63
    ociation
    -0.62
    reating
    -0.61
    ocating
    -0.60
    holding
    -0.60
    ivas
    -0.60
    POSITIVE LOGITS
     mornings
    1.20
     weekday
    0.89
    morning
    0.72
     morning
    0.70
    HTML
    0.66
     evenings
    0.65
     Thurs
    0.64
    uters
    0.61
    taboola
    0.61
     Saturdays
    0.61
    Activations Density 0.034%

    No Known Activations