© 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. 1-RES-JB
    11. 20412
    Prev
    Next
    INDEX
    Explanations

    references to specific days of the week

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "day" and its variations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ucket
    -0.67
    pmwiki
    -0.65
    inates
    -0.64
     Huff
    -0.62
    OTT
    -0.60
    otto
    -0.60
     spoiler
    -0.59
     Tra
    -0.59
    rail
    -0.59
     liner
    -0.58
    POSITIVE LOGITS
    days
    1.46
    theless
    1.02
    aturdays
    1.00
    pring
    0.97
    terday
    0.93
    soever
    0.93
    ertodd
    0.91
    ruary
    0.88
     mornings
    0.87
    lihood
    0.87
    Activations Density 0.012%

    No Known Activations