© 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. 8744
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal disputes and controversies

    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
    +0.19
    0.9%
    362
    +0.16
    0.7%
    512
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.19
    0.07
    393
    +0.16
    0.06
    608
    +0.12
    0.06
    Negative Logits
    mares
    -0.76
    Versions
    -0.72
    cies
    -0.71
     Includes
    -0.68
    each
    -0.66
     besides
    -0.65
     writes
    -0.65
    join
    -0.65
    thood
    -0.65
    vernment
    -0.64
    POSITIVE LOGITS
     easiest
    1.35
     hardest
    1.26
     same
    1.25
     safest
    1.22
     strongest
    1.20
     biggest
    1.19
     simplest
    1.19
     cornerstone
    1.19
     greatest
    1.17
     centerpiece
    1.16
    Activations Density 0.182%

    No Known Activations