Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 11465
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the city of Pittsburgh

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city of Pittsburgh and its associated sports teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phas
    -0.98
    perse
    -0.87
    hig
    -0.86
    pora
    -0.85
    nces
    -0.81
    arist
    -0.79
    lasses
    -0.79
    uchin
    -0.77
     NCT
    -0.77
    binding
    -0.75
    POSITIVE LOGITS
    sburgh
    1.64
     Penguins
    1.26
     Steelers
    1.26
    sylvania
    1.04
     Pirates
    0.99
     Mellon
    0.92
    sburg
    0.89
    Pitt
    0.85
     Pittsburgh
    0.80
    sylv
    0.80
    Activations Density 0.018%

    No Known Activations