© 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 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. 6167
    Prev
    Next
    INDEX
    Explanations

    phrases related to military personnel and armed forces

    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
    288
    +0.14
    0.6%
    447
    +0.13
    0.6%
    99
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.02
    294
    +0.13
    0.01
    516
    +0.10
    0.02
    Negative Logits
    omial
    -0.79
    âĶģ
    -0.77
    âĶĢâĶĢâĶĢâĶĢ
    -0.75
    TERN
    -0.75
    ologies
    -0.72
    tera
    -0.71
    aminer
    -0.71
    Solution
    -0.70
     Seller
    -0.69
     Bloom
    -0.66
    POSITIVE LOGITS
     stationed
    1.36
     fatig
    1.10
     barracks
    1.04
     garrison
    0.97
     patrolling
    0.95
     uniforms
    0.92
     colonel
    0.91
     guarding
    0.88
     soldiers
    0.86
     salute
    0.83
    Activations Density 0.040%

    No Known Activations