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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 21488
    Prev
    Next
    INDEX
    Explanations

    comparisons between different countries on various aspects such as economy, politics, and geography

    oai_token-act-pair · gpt-3.5-turbo

    references to comparisons between countries or nations

    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
     Clicker
    -0.80
     Cain
    -0.75
     Levine
    -0.72
    inventoryQuantity
    -0.71
     Pepe
    -0.70
     Elias
    -0.70
     Pupp
    -0.70
     Trayvon
    -0.68
     Reincarn
    -0.68
     Osiris
    -0.68
    POSITIVE LOGITS
     countries
    2.24
     nations
    2.09
     Countries
    1.89
     democracies
    1.83
     provinces
    1.67
     jurisdictions
    1.58
     regions
    1.56
     states
    1.52
     industrialized
    1.52
     territories
    1.48
    Activations Density 0.354%

    No Known Activations