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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 18734
    Prev
    Next
    INDEX
    Explanations

    time-related expressions like hours and days

    oai_token-act-pair · gpt-3.5-turbo

    references to time-related activities or schedules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.96
    çīĪ
    -0.77
     acronym
    -0.74
    ª
    -0.68
    inous
    -0.67
    entity
    -0.66
    ãĤ´
    -0.66
     slogans
    -0.65
    Platform
    -0.65
     trademarks
    -0.65
    POSITIVE LOGITS
     schedules
    1.00
     schedule
    0.99
     weekends
    0.96
    dule
    0.94
     vacations
    0.93
     circadian
    0.89
    idays
    0.89
     holidays
    0.89
     evenings
    0.88
     commute
    0.87
    Activations Density 1.112%

    No Known Activations