© 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. 200
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict or urgent situations

    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
    152
    +0.12
    0.6%
    216
    +0.12
    0.5%
    501
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.12
    0.04
    70
    +0.12
    0.04
    152
    +0.10
    0.04
    Negative Logits
    ãĤ¡
    -0.85
    metics
    -0.65
    ãĥª
    -0.61
    affle
    -0.61
     favor
    -0.59
     parity
    -0.58
    IJ
    -0.58
     matchups
    -0.57
    alty
    -0.57
     quotes
    -0.57
    POSITIVE LOGITS
     atop
    1.00
     indoors
    0.98
     peacefully
    0.97
     somewhere
    0.96
     abroad
    0.96
     ashore
    0.96
     inside
    0.93
     aboard
    0.92
     outdoors
    0.84
    outside
    0.83
    Activations Density 0.174%

    No Known Activations