© 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. 2-RES-JB
    11. 13813
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific nationality

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Afghan-related topics, particularly individuals and issues surrounding Afghanistan

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tower
    -0.81
    lag
    -0.79
    vous
    -0.78
    creen
    -0.77
    aminer
    -0.77
    ilver
    -0.75
    ynt
    -0.73
    erd
    -0.72
    nces
    -0.72
    incent
    -0.72
    POSITIVE LOGITS
     Afghan
    1.21
    istan
    1.17
    istani
    1.14
     Afghans
    1.09
     Afgh
    1.06
     Kabul
    0.98
     Taliban
    0.98
     Afghanistan
    0.96
    ghan
    0.92
     civilians
    0.83
    Activations Density 0.006%

    No Known Activations