© 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 3072
    9. 8-RES_FS3072-JB
    11. 252
    Prev
    Next
    INDEX
    Explanations

    phrases related to military operations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    +0.12
    0.6%
    314
    +0.10
    0.5%
    587
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    377
    +0.12
    0.07
    651
    +0.10
    0.06
    253
    +0.10
    0.05
    Negative Logits
    catentry
    -0.74
    inventoryQuantity
    -0.65
    eer
    -0.62
     Nanto
    -0.61
    ams
    -0.61
    Ĺ
    -0.59
    ppe
    -0.59
    aml
    -0.59
     Decay
    -0.58
    etus
    -0.58
    POSITIVE LOGITS
    abouts
    1.76
    tical
    1.44
    tics
    1.39
    tic
    1.08
     illegally
    0.87
    with
    0.85
    upon
    0.80
    comings
    0.71
    from
    0.70
     unlawfully
    0.69
    Activations Density 0.494%

    No Known Activations