© 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. 8-RES-JB
    11. 13131
    Prev
    Next
    INDEX
    Explanations

    numerical values in the form of the count of items

    oai_token-act-pair · gpt-3.5-turbo

    mentions of numbers, particularly the words "three" and "four."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    atown
    -0.78
    Ô
    -0.76
     Rica
    -0.76
    assetsadobe
    -0.72
     earthqu
    -0.67
    theless
    -0.67
    velt
    -0.67
    vel
    -0.66
    vantage
    -0.66
    vier
    -0.65
    POSITIVE LOGITS
    teenth
    1.28
     finalists
    1.05
    fold
    1.02
    some
    0.95
     largest
    0.93
     pillars
    0.91
     aforementioned
    0.91
     main
    0.88
    peat
    0.88
     biggest
    0.87
    Activations Density 0.100%

    No Known Activations