© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 8074
    Prev
    Next
    INDEX
    Explanations

    African countries

    oai_token-act-pair · gpt-3.5-turbo

    names of countries, particularly those associated with specific contexts or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sworth
    -0.93
    enegger
    -0.89
    earable
    -0.85
    ullivan
    -0.80
    rons
    -0.80
    sed
    -0.78
    ueller
    -0.78
    ancies
    -0.77
    oiler
    -0.77
    ulty
    -0.76
    POSITIVE LOGITS
     Congo
    1.21
     Angola
    1.00
     Tanzania
    0.97
     Zamb
    0.92
     Guinea
    0.91
     Myanmar
    0.91
     Cambodia
    0.91
     Zimbabwe
    0.89
     Senegal
    0.89
     Laos
    0.88
    Activations Density 0.017%

    No Known Activations