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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 9213
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "Malaysia."

    oai_token-act-pair · gpt-3.5-turbo

    references to Malaysia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.70
    ebook
    -0.69
    ptions
    -0.66
    tops
    -0.64
    minus
    -0.64
     brut
    -0.61
    soDeliveryDate
    -0.61
    á½
    -0.61
    UGC
    -0.61
    ¯¯
    -0.61
    POSITIVE LOGITS
     Lumpur
    1.62
     Airlines
    1.42
    awi
    0.83
     airliner
    0.82
    colm
    0.82
    aimon
    0.80
     Airways
    0.79
    vati
    0.79
    ovic
    0.77
     Abdul
    0.76
    Activations Density 0.024%

    No Known Activations