© 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. 1-RES-JB
    11. 3508
    Prev
    Next
    INDEX
    Explanations

    references to the football team "Bills."

    oai_token-act-pair · gpt-3.5-turbo

    references to the Buffalo Bills football team

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    judicial
    -0.72
    ller
    -0.70
    onym
    -0.68
     Nero
    -0.66
    pmwiki
    -0.66
    tle
    -0.66
    population
    -0.65
    vent
    -0.63
    yrinth
    -0.63
    severe
    -0.62
    POSITIVE LOGITS
     Bills
    1.47
     Sabres
    1.01
    iard
    0.95
    cakes
    0.84
    ukong
    0.83
    ertodd
    0.82
     Trace
    0.81
     Beaut
    0.78
    heed
    0.77
    backs
    0.77
    Activations Density 0.003%

    No Known Activations