© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3018
    Prev
    Next
    INDEX
    Explanations

    phrases related to sets or collections of items

    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
    393
    +0.12
    0.5%
    561
    +0.12
    0.5%
    587
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.12
    0.03
    568
    +0.12
    0.02
    561
    +0.11
    0.03
    Negative Logits
    hyde
    -0.85
    ashtra
    -0.76
    ivo
    -0.75
    eri
    -0.74
    erate
    -0.71
    ļéĨĴ
    -0.70
    Pet
    -0.69
    ablishment
    -0.69
    ration
    -0.68
    leness
    -0.68
    POSITIVE LOGITS
     stairs
    1.00
     handcuffs
    0.96
     rules
    0.91
     circumstances
    0.91
     facts
    0.91
     instructions
    0.90
     twins
    0.87
     footprints
    0.87
     keys
    0.87
     sorts
    0.87
    Activations Density 0.066%

    No Known Activations