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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 7280
    Prev
    Next
    INDEX
    Explanations

    phrases related to Western entities or regions

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Western."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    papers
    -0.74
    SourceFile
    -0.73
    ãĥ´ãĤ¡
    -0.71
    minecraft
    -0.68
    pod
    -0.68
     CODE
    -0.66
    eta
    -0.66
    verb
    -0.65
     sched
    -0.65
    jar
    -0.64
    POSITIVE LOGITS
     Western
    3.63
    Western
    3.15
     western
    2.65
     Eastern
    2.23
    western
    1.99
    Eastern
    1.95
     West
    1.64
     eastern
    1.63
     Northern
    1.46
     Southern
    1.46
    Activations Density 0.023%

    No Known Activations