© 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. 10-RES-JB
    11. 5752
    Prev
    Next
    INDEX
    Explanations

    professional sports teams

    oai_token-act-pair · gpt-3.5-turbo

    references to sports teams and notable figures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lim
    -0.66
    ãĥĦ
    -0.63
    afety
    -0.62
    racuse
    -0.61
    ":""},{"
    -0.60
    olver
    -0.59
     Learns
    -0.57
    WithNo
    -0.57
    norm
    -0.56
    ibus
    -0.56
    POSITIVE LOGITS
     all
    1.09
     among
    0.96
     respectively
    0.87
    all
    0.86
    among
    0.85
    none
    0.83
     amongst
    0.80
     ALL
    0.79
     rounding
    0.79
    All
    0.76
    Activations Density 0.498%

    No Known Activations