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. 6-RES-JB
    6. 16808
    Prev
    Next
    INDEX
    Explanations

    items related to schedules

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "schedule."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vironment
    -0.78
    inals
    -0.77
    geoning
    -0.75
    ternity
    -0.73
    tymology
    -0.73
    oks
    -0.71
    nai
    -0.69
    ilee
    -0.69
    lu
    -0.69
    pires
    -0.68
    POSITIVE LOGITS
     schedules
    1.10
    dule
    1.04
     schedule
    1.01
     TBD
    0.79
     Sched
    0.77
     calendars
    0.76
    DAQ
    0.75
     scheduling
    0.74
     calendar
    0.72
     assignments
    0.72
    Activations Density 0.025%

    No Known Activations