© 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. 0-RES-JB
    11. 18101
    Prev
    Next
    INDEX
    Explanations

    mentions of specific days, particularly Sundays

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Sunday."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     advoc
    -0.72
    glomer
    -0.68
    uct
    -0.66
    \<
    -0.65
     ported
    -0.64
    asive
    -0.64
    ases
    -0.63
    types
    -0.62
    isks
    -0.62
     issu
    -0.61
    POSITIVE LOGITS
     Sunday
    3.49
    Sunday
    2.90
     Saturday
    2.72
     Monday
    2.50
     Sundays
    2.38
     Friday
    2.38
     Wednesday
    2.25
     Thursday
    2.25
     Tuesday
    2.24
    Saturday
    2.19
    Activations Density 0.016%

    No Known Activations