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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17527
    Prev
    Next
    INDEX
    Explanations

    mentions of sports teams and their performance metrics

    oai_token-act-pair · gpt-3.5-turbo

    temporal references related to sports seasons and performance metrics

    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
     Cosponsors
    -0.78
    ļéĨĴ
    -0.70
    tube
    -0.67
    grain
    -0.67
     Telegraph
    -0.65
     concess
    -0.64
     Channel
    -0.63
     Jou
    -0.62
    yi
    -0.62
    Tube
    -0.62
    POSITIVE LOGITS
     playoff
    1.25
     playoffs
    1.16
     rebuilding
    1.07
     rebuild
    1.07
    uilding
    1.06
     postseason
    1.05
     cellar
    1.02
     Playoffs
    1.01
     relegation
    1.00
     standings
    1.00
    Activations Density 0.350%

    No Known Activations