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. 11-RES-JB
    6. 10972
    Prev
    Next
    INDEX
    Explanations

    locations and organizations related to Pakistan

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific locations and events related to Pakistan

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GNOME
    -0.93
    ovych
    -0.91
    âĤ¬
    -0.90
     Chrys
    -0.90
     Saturn
    -0.87
    ô
    -0.86
     Elena
    -0.85
    Greek
    -0.83
    ø
    -0.82
    Elsa
    -0.81
    POSITIVE LOGITS
     Pakistan
    2.18
     Islamabad
    2.15
    Pakistan
    2.14
     Pakistani
    2.13
     Karachi
    1.95
     Kashmir
    1.94
    Pak
    1.76
     Punjab
    1.73
     Sharif
    1.70
     Lah
    1.62
    Activations Density 0.342%

    No Known Activations