© 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 EvalsExportsinterp-engineNEWAPI 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. 18860
    Prev
    Next
    INDEX
    Explanations

    references to the Toronto Maple Leafs hockey team

    oai_token-act-pair · gpt-3.5-turbo

    references to the Toronto Maple Leafs and maple-related products

    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
    CVE
    -0.75
    ded
    -0.71
    glomer
    -0.66
    ulation
    -0.65
    iop
    -0.63
    ebook
    -0.63
    ega
    -0.61
    esson
    -0.61
    ners
    -0.60
    ses
    -0.60
    POSITIVE LOGITS
     Leafs
    1.37
     Leaf
    1.18
    Story
    1.15
     syrup
    1.05
    croft
    0.94
    leaf
    0.89
     Maple
    0.83
    cone
    0.81
    ãĥ³ãĤ¸
    0.77
    anut
    0.75
    Activations Density 0.050%

    No Known Activations