© 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. 11-RES-JB
    11. 166
    Prev
    Next
    INDEX
    Explanations

    mentions or discussions related to American football quarterbacks

    oai_token-act-pair · gpt-3.5-turbo

    terms related to football quarterbacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    henko
    -0.92
    pload
    -0.76
     queens
    -0.71
    bourg
    -0.71
    rawdownloadcloneembedreportprint
    -0.71
     Debor
    -0.67
    romy
    -0.65
    irlf
    -0.64
    tml
    -0.64
     Lauder
    -0.63
    POSITIVE LOGITS
     guru
    0.97
     whis
    0.94
     QB
    0.88
     coach
    0.87
     quarterback
    0.84
     Manziel
    0.82
     hurry
    0.77
     passer
    0.74
     Heisman
    0.74
     Colt
    0.74
    Activations Density 0.032%

    No Known Activations