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. 4-RES-JB
    6. 3796
    Prev
    Next
    INDEX
    Explanations

    mentions of different countries

    oai_token-act-pair · gpt-3.5-turbo

    references to countries and their situations in various contexts

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

    No Comments

    Negative Logits
    potion
    -0.76
    TEXTURE
    -0.76
    PDATE
    -0.76
    earable
    -0.71
    ilts
    -0.71
    iple
    -0.70
    thumbnails
    -0.69
     Pastebin
    -0.69
    sbm
    -0.68
    CHAT
    -0.67
    POSITIVE LOGITS
    wide
    1.03
     governments
    0.80
     countries
    0.78
     Governments
    0.76
     Arabia
    0.73
     nations
    0.70
     bordering
    0.69
     taxed
    0.69
     Uruguay
    0.69
     legalized
    0.68
    Activations Density 0.046%

    No Known Activations