© 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 3072
    9. 8-RES_FS3072-JB
    11. 229
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of wood

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    125
    +0.10
    0.4%
    582
    +0.09
    0.4%
    284
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.10
    326
    +0.09
    0.08
    99
    +0.09
    0.05
    Negative Logits
    enance
    -0.72
    glomer
    -0.68
    Vi
    -0.67
    ional
    -0.66
    FontSize
    -0.66
     orally
    -0.65
     Uriel
    -0.64
     Ces
    -0.64
    OPLE
    -0.63
    igation
    -0.63
    POSITIVE LOGITS
    ruff
    1.03
    lands
    0.99
    wood
    0.94
    vale
    0.94
    mere
    0.90
    hurst
    0.88
    \\\\\\\\
    0.86
    land
    0.86
    quist
    0.83
    sey
    0.81
    Activations Density 1.095%

    No Known Activations