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. 6-RES-JB
    6. 21673
    Prev
    Next
    INDEX
    Explanations

    countries as named entities, focusing primarily on Nepal

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the country Nepal and related geographical or cultural terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iveness
    -0.81
     Painter
    -0.78
    tower
    -0.75
    Slot
    -0.75
    ivity
    -0.75
    hips
    -0.75
    aunder
    -0.74
    rawdownloadcloneembedreportprint
    -0.74
    hement
    -0.72
    Thumbnail
    -0.71
    POSITIVE LOGITS
     Pradesh
    1.12
     Nepal
    1.07
    ayan
    0.92
     Nep
    0.78
     Himal
    0.76
     Everest
    0.76
     earthquake
    0.75
     nep
    0.74
    endra
    0.74
     Earthquake
    0.72
    Activations Density 0.034%

    No Known Activations