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. 8-RES-JB
    6. 3822
    Prev
    Next
    INDEX
    Explanations

    references to the country Indonesia

    oai_token-act-pair · gpt-3.5-turbo

    references to Indonesia and its related contexts

    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
    riers
    -0.77
    hare
    -0.75
    busters
    -0.73
    hire
    -0.69
    rost
    -0.68
    rieve
    -0.68
    aday
    -0.68
    ages
    -0.66
    umbnails
    -0.65
    sburgh
    -0.65
    POSITIVE LOGITS
     Airlines
    0.93
     Indonesia
    0.90
    ãħĭ
    0.86
     Indonesian
    0.84
     Peoples
    0.76
    istani
    0.75
     Strait
    0.75
     Jakarta
    0.75
    esi
    0.75
    iens
    0.74
    Activations Density 0.033%

    No Known Activations