© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 8200
    Prev
    Next
    INDEX
    Explanations

    locations or events related to Norway

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    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

    Neuron Alignment
    Index
    Value
    % of L₁
    481
    +0.14
    0.6%
    57
    +0.10
    0.4%
    52
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.14
    0.01
    65
    +0.10
    0.01
    67
    +0.10
    0.01
    Negative Logits
    ually
    -0.85
    place
    -0.83
    plain
    -0.80
    ###
    -0.78
    anooga
    -0.76
    ual
    -0.74
    ept
    -0.74
    ible
    -0.74
    icago
    -0.74
    heet
    -0.70
    POSITIVE LOGITS
     Bok
    1.04
    borg
    1.00
     Norway
    0.88
    wegian
    0.87
     Refugee
    0.80
     Andersen
    0.80
    ãĥ©ãĥ³
    0.77
    ø
    0.76
     Oslo
    0.75
    å
    0.75
    Activations Density 0.022%

    No Known Activations