© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 13761
    Prev
    Next
    INDEX
    Explanations

    phrases related to the status or activity of sports players

    oai_token-act-pair · gpt-3.5-turbo

    key events or conditions affecting players in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Panel
    -0.72
     Alma
    -0.70
     Feminist
    -0.67
    language
    -0.67
     Racial
    -0.66
    0002
    -0.66
     Transparency
    -0.65
    asonic
    -0.65
     Economist
    -0.65
     Rowling
    -0.64
    POSITIVE LOGITS
     sidelined
    1.35
     injured
    1.33
     healthy
    1.23
     injury
    1.14
     traded
    1.09
     rehab
    1.03
     retire
    1.03
     waived
    1.03
     retired
    1.01
     injuries
    0.97
    Activations Density 0.295%

    No Known Activations