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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16477
    Prev
    Next
    INDEX
    Explanations

    specific terms and events related to conflict zones and military operations, with a focus on mentions of armed groups like ISIS and military units like the Free Syrian Army

    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
    447
    +0.16
    0.7%
    154
    +0.13
    0.6%
    478
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.16
    0.04
    154
    +0.13
    0.04
    288
    +0.10
    0.04
    Negative Logits
     Einstein
    -0.88
    Consumer
    -0.82
     Whitney
    -0.81
     Spielberg
    -0.80
    Bloom
    -0.80
     Compton
    -0.79
     Dickens
    -0.77
     Mercury
    -0.76
     Donn
    -0.75
     Buffett
    -0.74
    POSITIVE LOGITS
     militias
    1.46
     rebels
    1.36
     militia
    1.34
     fighters
    1.24
     insurgents
    1.24
     militants
    1.16
     paramilitary
    1.13
     shelling
    1.12
     forces
    1.12
     commanders
    1.11
    Activations Density 0.152%

    No Known Activations