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. 6064
    Prev
    Next
    INDEX
    Explanations

    locations or proper nouns related to the country Nepal

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the country Nepal and related terms

    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
    =#
    -0.74
    istration
    -0.72
     Painter
    -0.69
    aunder
    -0.69
    erie
    -0.68
    hement
    -0.67
    dinand
    -0.67
    positive
    -0.67
    \\\\\\\\\\\\\\\\
    -0.66
    tower
    -0.64
    POSITIVE LOGITS
     Pradesh
    1.08
    ayan
    1.01
     Nepal
    0.99
     Everest
    0.81
     Airways
    0.80
     Himal
    0.78
    aya
    0.78
     Nep
    0.77
     Lanka
    0.77
     Kath
    0.76
    Activations Density 0.020%

    No Known Activations