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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RES-JB
    6. 7721
    Prev
    Next
    INDEX
    Explanations

    locations or entities related to the city of St. Louis

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "St. Louis."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ļéĨĴ
    -0.70
    =-=-=-=-=-=-=-=-
    -0.68
     corpus
    -0.66
    enegger
    -0.64
    zees
    -0.63
    vernment
    -0.62
    blers
    -0.61
     centrif
    -0.60
     destro
    -0.60
     matrix
    -0.59
    POSITIVE LOGITS
     Petersburg
    0.88
     Columb
    0.81
    ilda
    0.78
     Augustine
    0.77
     Clair
    0.75
     Louis
    0.73
    Va
    0.73
     Jude
    0.73
    rict
    0.73
     Vincent
    0.71
    Activations Density 0.029%

    No Known Activations