© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 10256
    Prev
    Next
    INDEX
    Explanations

    dates and time-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, specifically phrases indicating "this" or "last" week or month

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ahime
    -0.72
    ensitive
    -0.68
     knots
    -0.60
    velt
    -0.60
    anded
    -0.59
    oidal
    -0.59
    apego
    -0.57
    izontal
    -0.56
    Trend
    -0.56
    arte
    -0.55
    POSITIVE LOGITS
     weekend
    1.22
     afternoon
    1.21
     week
    1.18
     evening
    1.12
     morning
    1.10
     month
    1.02
     night
    0.95
     mornings
    0.92
     summer
    0.91
     evenings
    0.88
    Activations Density 0.146%

    No Known Activations