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. 1630
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to countries, with a specific focus on "Norway"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Norway and related terms or entities

    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
    ually
    -0.97
    ual
    -0.83
    place
    -0.81
    eenth
    -0.80
    ience
    -0.79
    uality
    -0.79
    uers
    -0.78
    icts
    -0.76
    uation
    -0.76
    icago
    -0.75
    POSITIVE LOGITS
    wegian
    0.90
    wich
    0.81
    gger
    0.73
    Ô
    0.70
    borg
    0.70
     Bok
    0.68
     Cla
    0.67
    pheus
    0.66
    MAL
    0.65
    poon
    0.65
    Activations Density 0.056%

    No Known Activations