© 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. 0-RES-JB
    11. 8183
    Prev
    Next
    INDEX
    Explanations

    mentions of sports teams, specifically the Los Angeles Dodgers and Los Angeles Lakers

    oai_token-act-pair · gpt-3.5-turbo

    references to the Los Angeles Dodgers and other MLB teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulf
    -0.65
    ect
    -0.64
    af
    -0.64
    MP
    -0.63
     accessed
    -0.61
     inspection
    -0.61
    iment
    -0.60
    afer
    -0.60
    ique
    -0.59
    ability
    -0.59
    POSITIVE LOGITS
     Dodgers
    3.63
     Lakers
    2.06
     Clippers
    2.00
     Padres
    1.89
     Braves
    1.68
     Yankees
    1.64
     Cubs
    1.62
     Phillies
    1.62
     Chargers
    1.58
     Dod
    1.58
    Activations Density 0.014%

    No Known Activations