© 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. 10349
    Prev
    Next
    INDEX
    Explanations

    information related to sports statistics and player transfers

    oai_token-act-pair · gpt-3.5-turbo

    unique separator tokens, particularly for structured data formats

    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
     corrid
    -0.79
    conservancy
    -0.75
    iosyncr
    -0.75
    .}
    -0.74
    soDeliveryDate
    -0.73
    slice
    -0.72
    leys
    -0.70
    ilogy
    -0.69
    aunted
    -0.69
    iaries
    -0.67
    POSITIVE LOGITS
     Male
    0.93
     âĵĺ
    0.92
     Yes
    0.92
     Difference
    0.90
     Female
    0.90
     Total
    0.89
     Gender
    0.87
     -----
    0.87
     Actual
    0.87
     ----------------
    0.86
    Activations Density 0.530%

    No Known Activations