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. 4-RES-JB
    6. 5760
    Prev
    Next
    INDEX
    Explanations

    days of the week, specifically "Tuesday"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the day of the week, specifically Tuesday

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

    No Comments

    Negative Logits
    abet
    -0.95
    ript
    -0.90
    luster
    -0.83
    egal
    -0.79
    respons
    -0.76
    ordes
    -0.76
    onductor
    -0.75
    keye
    -0.72
    agos
    -0.72
    ebook
    -0.71
    POSITIVE LOGITS
     morning
    1.48
     afternoon
    1.37
     night
    1.31
     evening
    1.29
     mornings
    1.20
     Night
    1.07
    morning
    1.06
     nights
    1.04
     evenings
    0.97
     Morning
    0.94
    Activations Density 0.041%

    No Known Activations