© 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. 12159
    Prev
    Next
    INDEX
    Explanations

    measurements related to physical distances or sizes

    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
    481
    +0.13
    0.6%
    255
    +0.12
    0.5%
    618
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.13
    0.02
    162
    +0.12
    0.02
    657
    +0.10
    0.02
    Negative Logits
    NetMessage
    -0.74
    PsyNetMessage
    -0.72
    HCR
    -0.71
    enegger
    -0.67
    ä½ľ
    -0.66
    jri
    -0.64
    SpaceEngineers
    -0.63
    krit
    -0.60
    EStreamFrame
    -0.60
    ãĥ´ãĤ¡
    -0.59
    POSITIVE LOGITS
    ometers
    0.97
    cake
    0.92
    glass
    0.92
    wise
    0.90
    ages
    0.89
    asus
    0.86
    age
    0.84
    ometer
    0.83
    aires
    0.81
    icity
    0.81
    Activations Density 0.076%

    No Known Activations