© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 6859
    Prev
    Next
    INDEX
    Explanations

    names of sports teams

    oai_token-act-pair · gpt-3.5-turbo

    the names of sports teams, particularly focusing on "Blue" and "Red" teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    schild
    -0.99
    enegger
    -0.92
    chwitz
    -0.85
    é¾įå¥ij士
    -0.79
     Duterte
    -0.75
    ĸļ
    -0.72
     Shant
    -0.71
    staking
    -0.71
     relativity
    -0.71
    aeda
    -0.69
    POSITIVE LOGITS
     Devils
    1.06
    birds
    1.06
    hawks
    1.06
     Falcons
    1.04
     Panthers
    1.04
     Bucs
    1.03
     Yankees
    0.99
     Packers
    0.98
     Riders
    0.97
     Lions
    0.97
    Activations Density 0.218%

    No Known Activations