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

    Neuronpedia

    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. 10541
    Prev
    Next
    INDEX
    Explanations

    mentions of the Australian Football League (AFL)

    oai_token-act-pair · gpt-3.5-turbo

    references to the AFL (Australian Football League) and related teams or players

    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
     Buc
    -0.85
    Ohio
    -0.80
    agy
    -0.77
    imaru
    -0.76
     Cleveland
    -0.74
     Kasich
    -0.74
    Ô
    -0.73
    anka
    -0.72
    DonaldTrump
    -0.72
     Tsarnaev
    -0.71
    POSITIVE LOGITS
    elaide
    1.12
     Tasmania
    1.08
     NSW
    1.05
    elong
    1.03
     NRL
    1.00
     Turnbull
    0.99
     Adelaide
    0.99
     Australian
    0.97
     Brisbane
    0.97
     AFL
    0.96
    Activations Density 0.103%

    No Known Activations