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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16848
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Indonesia

    oai_token-act-pair · gpt-3.5-turbo

    references to Indonesia in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fare
    -0.80
    riers
    -0.79
    hire
    -0.78
    busters
    -0.72
    hare
    -0.71
    VEL
    -0.70
    ages
    -0.69
    umbnails
    -0.69
    abolic
    -0.68
    abet
    -0.68
    POSITIVE LOGITS
     Indonesia
    0.98
     Airlines
    0.95
     Indonesian
    0.87
    ãħĭ
    0.85
     Jakarta
    0.85
     Indones
    0.83
    istani
    0.81
     Papua
    0.79
     Peoples
    0.75
     Lamp
    0.75
    Activations Density 0.021%

    No Known Activations