© 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. 8-RES-JB
    11. 6954
    Prev
    Next
    INDEX
    Explanations

    mentions of American football terms related to the offensive side of the game

    oai_token-act-pair · gpt-3.5-turbo

    references to offensive play in sports contexts

    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
     Solitaire
    -0.93
    bourg
    -0.84
    20439
    -0.79
    Deal
    -0.78
    ilk
    -0.74
    arnaev
    -0.74
    hyde
    -0.73
    iless
    -0.72
    chell
    -0.71
    aco
    -0.71
    POSITIVE LOGITS
     linemen
    1.19
     lineman
    1.14
     coordinator
    0.87
     firepower
    0.87
     coaches
    0.82
     prowess
    0.81
     offensive
    0.79
     rebounds
    0.77
     tackle
    0.76
     coordin
    0.76
    Activations Density 0.022%

    No Known Activations