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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 41762
    Prev
    Next
    INDEX
    Explanations

    commands related to software package management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    508
    +0.10
    0.4%
    119
    +0.10
    0.4%
    347
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.10
    0.01
    355
    +0.10
    0.01
    727
    +0.10
    0.01
    Negative Logits
    issance
    -0.75
    mares
    -0.74
    ffield
    -0.70
    teenth
    -0.68
    iths
    -0.65
     afore
    -0.64
     Brotherhood
    -0.64
    ysis
    -0.64
    ORPG
    -0.62
     enthusi
    -0.62
    POSITIVE LOGITS
    help
    0.95
    sil
    0.92
    iframe
    0.88
    enable
    0.87
    global
    0.85
    tags
    0.85
    gpu
    0.84
    dry
    0.79
    save
    0.77
    disable
    0.76
    Activations Density 0.013%

    No Known Activations