© 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. 11269
    Prev
    Next
    INDEX
    Explanations

    words related to nighttime or the act of spending the night

    oai_token-act-pair · gpt-3.5-turbo

    references to "nights" or "evenings."

    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
     Reprodu
    -0.69
    ported
    -0.68
    artisan
    -0.64
    ogn
    -0.62
    ector
    -0.62
    anium
    -0.61
     cle
    -0.61
     vector
    -0.60
     proceeding
    -0.59
    ocrat
    -0.58
    POSITIVE LOGITS
     nights
    3.94
     evenings
    2.72
     mornings
    2.41
     Nights
    2.11
     weekends
    1.93
     summers
    1.83
     Saturdays
    1.71
     days
    1.67
     Sundays
    1.66
     winters
    1.62
    Activations Density 0.018%

    No Known Activations