© 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. 9583
    Prev
    Next
    INDEX
    Explanations

    technical instructions or commands related to software development

    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
    766
    +0.10
    0.5%
    665
    +0.09
    0.4%
    177
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.10
    0.03
    269
    +0.09
    0.02
    97
    +0.09
    0.02
    Negative Logits
     hurled
    -0.84
     conveyed
    -0.78
     flung
    -0.72
     employed
    -0.67
    released
    -0.66
     struck
    -0.65
    Released
    -0.64
    iated
    -0.64
    iating
    -0.64
     nailed
    -0.64
    POSITIVE LOGITS
     www
    1.12
     Settings
    1.04
     Preferences
    0.88
     Downloads
    0.87
     STATS
    0.78
     Gaal
    0.77
     http
    0.76
     Documents
    0.75
     Menu
    0.72
     page
    0.71
    Activations Density 0.069%

    No Known Activations