© 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. 4-RES-JB
    11. 592
    Prev
    Next
    INDEX
    Explanations

    words related to physical competitions or contests

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the term "bout" in various contexts

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

    No Comments

    Negative Logits
     Schiff
    -0.72
     Roads
    -0.67
    SOURCE
    -0.66
     fry
    -0.62
    operated
    -0.62
    washed
    -0.60
     Rica
    -0.60
     Mars
    -0.60
    isner
    -0.60
    sea
    -0.59
    POSITIVE LOGITS
     bout
    1.10
    iques
    1.08
     bouts
    1.00
    igraph
    0.81
     Bout
    0.77
    ãĥ¼ãĤ¯
    0.76
    fort
    0.75
     engagements
    0.73
    dayName
    0.73
    cakes
    0.70
    Activations Density 0.009%

    No Known Activations