© 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. 10-RES-JB
    11. 13915
    Prev
    Next
    INDEX
    Explanations

    terms related to professional sports leagues, particularly the National Hockey League (NHL) and American Hockey League (AHL)

    oai_token-act-pair · gpt-3.5-turbo

    references to hockey and football

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rises
    -0.74
     externalToEVAOnly
    -0.72
     burner
    -0.72
    heric
    -0.69
    romy
    -0.69
    atche
    -0.67
    ILE
    -0.65
     martial
    -0.63
    iven
    -0.63
    ardless
    -0.63
    POSITIVE LOGITS
     Association
    1.19
     League
    1.12
     Federation
    1.03
     Writers
    1.01
     Associ
    0.98
     Reference
    0.94
     Playoff
    0.93
     Abstract
    0.91
    League
    0.89
     Grounds
    0.85
    Activations Density 0.050%

    No Known Activations