© 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. 6-RES-JB
    11. 14458
    Prev
    Next
    INDEX
    Explanations

    references to countries, especially focusing on Saudi Arabia

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Saudi Arabia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onym
    -0.70
    ãĥ£
    -0.68
    HAEL
    -0.66
    erb
    -0.64
    berries
    -0.64
    early
    -0.64
    matter
    -0.62
    soDeliveryDate
    -0.62
    POS
    -0.62
     codec
    -0.62
    POSITIVE LOGITS
     Arabia
    1.59
     Arabian
    1.13
     Aram
    0.97
    doms
    0.87
    anism
    0.84
    iyah
    0.72
    istan
    0.72
     Saud
    0.71
     Riy
    0.71
     Airlines
    0.69
    Activations Density 0.021%

    No Known Activations