© 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. 6-RES-JB
    11. 11911
    Prev
    Next
    INDEX
    Explanations

    days of the week, especially Monday

    oai_token-act-pair · gpt-3.5-turbo

    mentions of days of the week, particularly in the context of events or actions

    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
    heid
    -0.79
    itar
    -0.71
    abet
    -0.70
    ample
    -0.70
    atorial
    -0.70
    ebook
    -0.70
    ordes
    -0.69
    pend
    -0.68
    aeus
    -0.68
    ancies
    -0.68
    POSITIVE LOGITS
     morning
    1.67
     afternoon
    1.61
     evening
    1.48
     night
    1.43
     mornings
    1.30
    morning
    1.29
     Morning
    1.09
     evenings
    1.05
     nights
    1.05
     Night
    1.03
    Activations Density 0.099%

    No Known Activations