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. 12094
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "Norway"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Norway and its derivatives

    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
    ual
    -0.80
    place
    -0.79
    uers
    -0.78
    aging
    -0.77
    ually
    -0.77
    ept
    -0.75
    plain
    -0.74
    xxxxxxxx
    -0.73
    uring
    -0.71
    enance
    -0.70
    POSITIVE LOGITS
     Bok
    1.03
    borg
    0.95
     Norway
    0.93
    wegian
    0.92
     Refugee
    0.91
     Norwegian
    0.85
     Oslo
    0.84
     Airlines
    0.81
     Dag
    0.78
    Ń·
    0.75
    Activations Density 0.016%

    No Known Activations