© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 1186
    Prev
    Next
    INDEX
    Explanations

    references to the day of the week 'Friday'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the day "Friday" and its context in time-related statements

    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
    ership
    -0.94
    hip
    -0.81
    abet
    -0.79
    respons
    -0.79
    aeda
    -0.77
    ports
    -0.77
    ris
    -0.76
    atem
    -0.76
    vironment
    -0.75
    lessly
    -0.74
    POSITIVE LOGITS
     morning
    1.37
     afternoon
    1.34
     night
    1.23
     evening
    1.17
     Night
    1.13
     mornings
    1.09
     nights
    1.04
    Night
    0.90
     twilight
    0.88
     evenings
    0.87
    Activations Density 0.042%

    No Known Activations