© 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 24576
    9. 8-RES_FS24576-JB
    11. 1415
    Prev
    Next
    INDEX
    Explanations

    ties to accidents or physical harm

    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
    289
    +0.10
    0.4%
    362
    +0.10
    0.4%
    188
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.03
    608
    +0.10
    0.03
    281
    +0.09
    0.02
    Negative Logits
    iety
    -0.79
    ctuary
    -0.76
    ieties
    -0.72
    itone
    -0.71
    iland
    -0.70
    istry
    -0.70
    Reviewed
    -0.70
    keep
    -0.70
     ancest
    -0.67
    keeping
    -0.66
    POSITIVE LOGITS
     gunfire
    1.18
     lightning
    1.08
     blows
    0.95
     bullets
    0.94
     blow
    0.92
     projectiles
    0.91
     iceberg
    0.91
     debris
    0.88
     punches
    0.85
     Hurricane
    0.85
    Activations Density 0.101%

    No Known Activations