© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 18708
    Prev
    Next
    INDEX
    Explanations

    mentions of specific durations of time in seconds

    oai_token-act-pair · gpt-3.5-turbo

    mentions of time durations, specifically in seconds

    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
    rim
    -0.77
    ramid
    -0.76
    oret
    -0.71
    artisan
    -0.71
    hemoth
    -0.70
    hammer
    -0.68
    ãĥĢ
    -0.67
    hus
    -0.67
    rex
    -0.65
    LECT
    -0.64
    POSITIVE LOGITS
     elapsed
    1.15
     seconds
    1.06
    seconds
    1.00
     Seconds
    0.92
     msec
    0.90
    aneously
    0.89
     milliseconds
    0.87
    ilver
    0.85
     baseman
    0.79
     mins
    0.78
    Activations Density 0.011%

    No Known Activations