Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 583
    Prev
    Next
    INDEX
    Explanations

    information related to countries and states, particularly focusing on economic status and political traits

    oai_token-act-pair · gpt-3.5-turbo

    references to countries and their socio-economic status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itness
    -0.74
     shops
    -0.71
    Connell
    -0.69
    paio
    -0.69
    mails
    -0.68
    ullivan
    -0.68
     synagogue
    -0.68
    ricks
    -0.67
    Tube
    -0.67
    Items
    -0.67
    POSITIVE LOGITS
     Asia
    1.09
     Africa
    1.09
     Confederation
    1.09
     continental
    1.04
     globe
    1.04
     industrialized
    1.03
     countries
    1.02
     democracies
    1.02
     Europe
    1.01
     nations
    0.99
    Activations Density 0.252%

    No Known Activations