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. 12742
    Prev
    Next
    INDEX
    Explanations

    measurements of time such as hours, days, and weeks

    oai_token-act-pair · gpt-3.5-turbo

    references to time and duration, particularly focusing on hours and days

    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
    dinand
    -0.83
    gently
    -0.76
     Flavoring
    -0.74
    uyomi
    -0.73
    tarian
    -0.73
    plex
    -0.73
    ãĥ´ãĤ¡
    -0.70
    mson
    -0.68
    acted
    -0.68
    JV
    -0.67
    POSITIVE LOGITS
     spent
    1.07
    hift
    1.00
     elapsed
    0.96
    pread
    0.93
    pring
    0.92
    cale
    0.91
     allotted
    0.90
     ago
    0.87
    ynthesis
    0.86
     wasted
    0.83
    Activations Density 0.169%

    No Known Activations