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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 7463
    Prev
    Next
    INDEX
    Explanations

    commands related to compiling, running, and profiling programs

    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
    218
    +0.13
    0.6%
    270
    +0.11
    0.5%
    497
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.02
    270
    +0.11
    0.02
    226
    +0.10
    0.02
    Negative Logits
    ylum
    -0.83
    omical
    -0.78
    opol
    -0.75
    ighter
    -0.74
    ayer
    -0.69
    ids
    -0.68
    bourg
    -0.65
    iatus
    -0.65
    illy
    -0.65
    ussen
    -0.64
    POSITIVE LOGITS
    tests
    0.96
     GNU
    0.81
     tests
    0.79
    command
    0.79
    escape
    0.77
     commands
    0.75
     PowerShell
    0.74
     Tests
    0.73
    times
    0.72
    linux
    0.72
    Activations Density 0.048%

    No Known Activations