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

    Neuronpedia

    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. 1-RES-JB
    11. 14561
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Pakistani" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to Pakistan and its citizens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umbnails
    -0.88
    aunder
    -0.82
    phasis
    -0.80
    rost
    -0.79
    paio
    -0.76
     rob
    -0.73
     Lys
    -0.72
    uer
    -0.72
    uden
    -0.72
    lopp
    -0.71
    POSITIVE LOGITS
    istani
    1.52
     Pakistani
    1.21
    Pakistan
    1.03
    Pak
    0.96
     Pakistan
    0.94
     Islamabad
    0.91
     Karachi
    0.89
     Taliban
    0.87
     Punjab
    0.83
     Nadu
    0.80
    Activations Density 0.006%

    No Known Activations