Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 18280
    Prev
    Next
    INDEX
    Explanations

    names of Norwegian individuals and entities

    oai_token-act-pair · gpt-3.5-turbo

    references to Norway 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 @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    plain
    -0.78
    heet
    -0.77
     Mayweather
    -0.75
    ilage
    -0.75
    DonaldTrump
    -0.71
    nyder
    -0.69
    heres
    -0.65
    acre
    -0.64
     Indianapolis
    -0.63
    utters
    -0.63
    POSITIVE LOGITS
    borg
    1.16
     Andersen
    1.04
     Bok
    1.04
    ø
    0.99
     Denmark
    0.99
     Danish
    0.96
     Ragnar
    0.95
     Norway
    0.93
     Scandinavian
    0.92
     Copenhagen
    0.92
    Activations Density 0.040%

    No Known Activations