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. 3-RES-JB
    6. 2335
    Prev
    Next
    INDEX
    Explanations

    words related to schedules, timings, and events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "schedule" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vironment
    -0.73
    vertisement
    -0.72
    Nich
    -0.70
    EStreamFrame
    -0.70
     Geh
    -0.69
    tymology
    -0.69
    ternity
    -0.69
    hiro
    -0.68
    ston
    -0.67
    doms
    -0.67
    POSITIVE LOGITS
    dule
    1.19
     schedule
    1.09
     schedules
    1.05
     scheduling
    0.82
     Schedule
    0.82
     calendars
    0.78
     calendar
    0.78
     Sched
    0.75
     cooker
    0.73
     assignments
    0.72
    Activations Density 0.018%

    No Known Activations