© 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. 24017
    Prev
    Next
    INDEX
    Explanations

    numbers related to the composition of sports teams

    oai_token-act-pair · gpt-3.5-turbo

    numeric representations related to roster sizes and ages in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Balk
    -0.77
     Twain
    -0.70
     classics
    -0.65
     popcorn
    -0.63
     Balkans
    -0.61
     Thrones
    -0.60
     adversity
    -0.60
     Rocky
    -0.60
     gum
    -0.59
     mimic
    -0.58
    POSITIVE LOGITS
    degree
    1.32
    percent
    1.27
    year
    1.19
    yard
    1.10
    caliber
    1.06
    page
    1.05
    minute
    1.04
    50
    1.00
    hour
    0.99
    years
    0.98
    Activations Density 0.090%

    No Known Activations