© 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. 21045
    Prev
    Next
    INDEX
    Explanations

    phrases related to injuries and returning to activities after recovery

    oai_token-act-pair · gpt-3.5-turbo

    mentions of player injuries and their expected returns 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
    76561
    -0.78
    nih
    -0.74
     Kirin
    -0.66
    perial
    -0.65
    Ocean
    -0.61
    zn
    -0.61
    ById
    -0.61
    Property
    -0.61
    rir
    -0.60
     Shib
    -0.60
    POSITIVE LOGITS
     sooner
    1.05
     Week
    1.05
     Saturday
    0.98
     Sunday
    0.97
     tomorrow
    0.97
     tonight
    0.96
     opener
    0.94
     Thursday
    0.94
    jured
    0.91
     Wednesday
    0.89
    Activations Density 0.150%

    No Known Activations