© 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. 10-RES-JB
    11. 17502
    Prev
    Next
    INDEX
    Explanations

    words related to the Middle East region

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Middle East

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bats
    -0.92
    é¾
    -0.80
    Seattle
    -0.77
    username
    -0.76
    yout
    -0.76
    ingham
    -0.75
    é¾įå
    -0.75
    iple
    -0.75
    onym
    -0.74
    inventoryQuantity
    -0.74
    POSITIVE LOGITS
     countries
    1.10
     Countries
    1.05
     nations
    1.04
     region
    0.99
     peace
    0.98
     dictators
    0.98
     Emir
    0.96
     Terrorism
    0.95
     Peace
    0.93
     instability
    0.92
    Activations Density 0.052%

    No Known Activations