© 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. 3-RES-JB
    11. 12951
    Prev
    Next
    INDEX
    Explanations

    words related to countries or nations

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific country or the concept of a country in general

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.82
    imilar
    -0.80
    LEASE
    -0.77
    ctory
    -0.76
    sbm
    -0.76
    urations
    -0.75
    ovember
    -0.74
    ritch
    -0.74
    ocry
    -0.73
    wcsstore
    -0.72
    POSITIVE LOGITS
    wide
    1.33
    oslov
    0.97
    side
    0.90
    men
    0.89
     Laos
    0.82
     Albania
    0.79
     Airlines
    0.79
     Ãľ
    0.78
     bombed
    0.74
     Algeria
    0.73
    Activations Density 0.047%

    No Known Activations