© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3-RES-JB
    11. 16889
    Prev
    Next
    INDEX
    Explanations

    keywords related to sports playoffs

    oai_token-act-pair · gpt-3.5-turbo

    references to playoff events in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    polit
    -0.77
    EMA
    -0.75
    metic
    -0.75
    Ly
    -0.73
    metics
    -0.72
    lev
    -0.72
    iard
    -0.72
    eworld
    -0.71
    gun
    -0.71
    gow
    -0.70
    POSITIVE LOGITS
     playoff
    0.93
     berth
    0.88
     playoffs
    0.84
     Rookie
    0.83
     MVP
    0.80
     bracket
    0.79
     rookie
    0.78
     games
    0.78
     matchups
    0.77
     semifinals
    0.77
    Activations Density 0.006%

    No Known Activations