© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 10041
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "Philippines"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Philippines

    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
     doom
    -0.72
    sle
    -0.71
    ti
    -0.67
     syn
    -0.65
    omer
    -0.65
     shut
    -0.64
     lock
    -0.64
     hiber
    -0.62
     err
    -0.62
    isen
    -0.60
    POSITIVE LOGITS
     Philippines
    4.00
     Philippine
    2.78
     Filipino
    2.37
     Manila
    2.35
     Filip
    1.96
     Duterte
    1.92
    Philipp
    1.86
    uterte
    1.83
     Dominican
    1.63
     Bahamas
    1.62
    Activations Density 0.013%

    No Known Activations