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. 17000
    Prev
    Next
    INDEX
    Explanations

    mentions of countries, specifically focusing on references to Belgium

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Belgium and Belarus

    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
    mitting
    -0.75
    pter
    -0.72
    seeking
    -0.72
    yy
    -0.72
    ãģ¦
    -0.69
    ning
    -0.68
    ilitating
    -0.67
    ticket
    -0.66
    mits
    -0.66
    apers
    -0.65
    POSITIVE LOGITS
     Congo
    0.98
    ois
    0.92
    rave
    0.87
     Admir
    0.80
    ians
    0.75
    ienne
    0.74
    gian
    0.73
     Columb
    0.70
    ucky
    0.68
     Macron
    0.68
    Activations Density 0.042%

    No Known Activations