© 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. 20505
    Prev
    Next
    INDEX
    Explanations

    references to the winter season or events related to it

    oai_token-act-pair · gpt-3.5-turbo

    references to winter-themed events or locations

    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
    inates
    -0.88
    riad
    -0.84
    ulhu
    -0.79
    onent
    -0.75
    -|
    -0.74
    atem
    -0.72
    tical
    -0.71
    Cu
    -0.70
    ean
    -0.70
    %]
    -0.70
    POSITIVE LOGITS
     Winter
    1.12
    winter
    1.02
    Winter
    1.01
     rink
    0.99
    thur
    0.97
     Wonderland
    0.93
    fell
    0.86
     Wolves
    0.84
     Jackets
    0.79
     Olympics
    0.76
    Activations Density 0.004%

    No Known Activations