Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20996
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical locations in the Middle East, particularly focused on policy and conflict

    oai_token-act-pair · gpt-3.5-turbo

    references to the Middle East and Africa

    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
    bats
    -0.79
     Pru
    -0.77
    pants
    -0.77
    onymous
    -0.77
    veyard
    -0.76
    neapolis
    -0.76
    unciation
    -0.75
    soType
    -0.74
    yard
    -0.73
    ueless
    -0.73
    POSITIVE LOGITS
     countries
    1.05
     nations
    1.04
     Countries
    1.02
     region
    1.00
     dictators
    0.95
     continent
    0.93
     Region
    0.92
     Terrorism
    0.91
     Regional
    0.91
     peace
    0.90
    Activations Density 0.089%

    No Known Activations