© 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. 7-RES-JB
    11. 12593
    Prev
    Next
    INDEX
    Explanations

    countries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of countries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terness
    -0.81
    itiveness
    -0.75
     quotes
    -0.71
    76561
    -0.69
    owe
    -0.68
     attributes
    -0.65
    ynes
    -0.63
    gru
    -0.62
    endum
    -0.61
    peed
    -0.60
    POSITIVE LOGITS
     Guam
    0.93
     Taiwan
    0.87
     Azerb
    0.85
     Marshall
    0.80
     Greenland
    0.78
     Samoa
    0.77
    Tai
    0.77
     Philippines
    0.76
     Kazakhstan
    0.76
     Archangel
    0.75
    Activations Density 0.073%

    No Known Activations