© 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 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. 3-RES-JB
    11. 5088
    Prev
    Next
    INDEX
    Explanations

    abbreviations related to Major League Baseball (MLB)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Major League Baseball (MLB)

    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
    comings
    -0.88
     Debor
    -0.83
    flies
    -0.78
    forth
    -0.77
    tops
    -0.76
    fulness
    -0.75
    combe
    -0.72
    atche
    -0.72
     MacArthur
    -0.70
    oldemort
    -0.69
    POSITIVE LOGITS
     Baseball
    0.89
     stadiums
    0.83
     pitcher
    0.82
     apparel
    0.81
    BIP
    0.79
     postseason
    0.78
     baseball
    0.78
     MLB
    0.77
     pitchers
    0.76
    ISO
    0.75
    Activations Density 0.009%

    No Known Activations