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. 10-RES-JB
    6. 11801
    Prev
    Next
    INDEX
    Explanations

    references to countries or matters related to countries

    oai_token-act-pair · gpt-3.5-turbo

    references to countries in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.82
    earable
    -0.82
    iple
    -0.81
    sbm
    -0.75
    aminer
    -0.74
    potion
    -0.74
    ocry
    -0.74
    TEXTURE
    -0.72
    odox
    -0.72
    \\\\\\\\
    -0.71
    POSITIVE LOGITS
     bordering
    1.06
     countries
    1.03
     Countries
    0.95
     governments
    0.93
     nations
    0.91
     nationals
    0.90
     abroad
    0.87
     exporting
    0.84
    men
    0.84
     Arabia
    0.83
    Activations Density 0.085%

    No Known Activations