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. 20908
    Prev
    Next
    INDEX
    Explanations

    geographical locations related to African countries

    oai_token-act-pair · gpt-3.5-turbo

    names of countries and regions involved in geopolitical issues

    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
    Denver
    -0.83
    rons
    -0.79
    ichick
    -0.77
    sed
    -0.76
    alty
    -0.75
    creen
    -0.75
    sburgh
    -0.73
    Pitt
    -0.71
    wcsstore
    -0.69
     Denver
    -0.68
    POSITIVE LOGITS
    andan
    0.99
     Congo
    0.95
     Nigeria
    0.94
    ese
    0.92
     Zimbabwe
    0.91
     Erit
    0.91
     Sudan
    0.90
     Leone
    0.89
     Haram
    0.89
     Africa
    0.87
    Activations Density 0.089%

    No Known Activations