© 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 12288
    9. 8-RES_FS12288-JB
    11. 9534
    Prev
    Next
    INDEX
    Explanations

    em dashes indicating a shift or interruption in the text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    314
    +0.24
    1.2%
    160
    +0.21
    1.0%
    102
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.24
    0.04
    442
    +0.21
    0.03
    102
    +0.15
    0.03
    Negative Logits
     whistle
    -0.77
     carriage
    -0.77
     lucky
    -0.76
     metic
    -0.75
     sled
    -0.74
     swarm
    -0.73
     kil
    -0.72
     plaque
    -0.71
     relocation
    -0.71
     rubble
    -0.70
    POSITIVE LOGITS
    that
    1.42
    requ
    1.42
    should
    1.42
    when
    1.41
    would
    1.40
    where
    1.40
    could
    1.36
    until
    1.36
    without
    1.35
    these
    1.34
    Activations Density 0.063%

    No Known Activations