© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1663
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "built-in."

    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
    435
    +0.11
    0.5%
    408
    +0.10
    0.5%
    653
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    435
    +0.11
    0.01
    408
    +0.10
    0.01
    398
    +0.10
    0.01
    Negative Logits
    ĸļ
    -0.96
    ÄŁ
    -0.93
    Ń·
    -0.87
    anches
    -0.87
    ģ«
    -0.83
    kk
    -0.81
    anship
    -0.79
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.79
    phia
    -0.78
    Ĺ
    -0.78
    POSITIVE LOGITS
     extras
    0.87
     functionality
    0.83
     support
    0.80
     mechanism
    0.79
     features
    0.78
     auto
    0.78
     omn
    0.78
     complication
    0.77
     capability
    0.76
     scripting
    0.75
    Activations Density 0.031%

    No Known Activations