© 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. 2-RES-JB
    11. 13698
    Prev
    Next
    INDEX
    Explanations

    mentions of the city of Pittsburgh

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city of Pittsburgh and its affiliated sports teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hig
    -0.90
    arist
    -0.86
    lasses
    -0.79
    binding
    -0.73
    nda
    -0.72
    lass
    -0.70
    uchin
    -0.69
    perse
    -0.69
    tle
    -0.68
    BOOK
    -0.68
    POSITIVE LOGITS
    sburgh
    1.83
     Steelers
    1.28
     Penguins
    1.23
     Pittsburgh
    1.06
    sburg
    1.03
     Mellon
    1.02
    Pitt
    0.94
     Pirates
    0.94
    sylvania
    0.94
     Tribune
    0.82
    Activations Density 0.007%

    No Known Activations