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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 9913
    Prev
    Next
    INDEX
    Explanations

    the day of the week, specifically "Friday"

    oai_token-act-pair · gpt-3.5-turbo

    specific references to the day "Friday."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ership
    -0.96
    ById
    -0.73
    fect
    -0.71
    ategory
    -0.70
    ate
    -0.70
    trak
    -0.70
    colour
    -0.70
    hip
    -0.70
    ample
    -0.68
    amples
    -0.68
    POSITIVE LOGITS
     afternoon
    1.75
     morning
    1.73
     night
    1.73
     evening
    1.69
     nights
    1.42
     mornings
    1.41
     Night
    1.40
     evenings
    1.33
    night
    1.24
     dusk
    1.14
    Activations Density 0.061%

    No Known Activations