© 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. 2-RES-JB
    11. 11623
    Prev
    Next
    INDEX
    Explanations

    terms related to sports competitions or contests

    oai_token-act-pair · gpt-3.5-turbo

    terms related to competitive events or pairings, particularly in sports and matchups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aug
    -0.81
    organic
    -0.79
    aum
    -0.79
    ryn
    -0.78
    lear
    -0.75
    âĵĺ
    -0.75
    child
    -0.75
    ricular
    -0.74
    ogy
    -0.74
    rib
    -0.73
    POSITIVE LOGITS
     matchups
    1.18
     matchup
    1.10
     Advantage
    0.79
     Finder
    0.78
     Tonight
    0.78
     mismatch
    0.76
     opponents
    0.74
     opponent
    0.74
     foes
    0.71
     Encounter
    0.71
    Activations Density 0.006%

    No Known Activations