© 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. 8581
    Prev
    Next
    INDEX
    Explanations

    lessons or insights from events or actions

    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
    438
    +0.11
    0.5%
    615
    +0.11
    0.5%
    575
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.11
    0.02
    324
    +0.11
    0.02
    98
    +0.10
    0.02
    Negative Logits
     occupancy
    -0.75
    endars
    -0.68
     lobb
    -0.66
    omin
    -0.63
    roid
    -0.63
     flush
    -0.62
    umbers
    -0.62
     contiguous
    -0.61
    trak
    -0.61
    rencies
    -0.60
    POSITIVE LOGITS
     Learned
    1.48
     learned
    1.22
    Lear
    1.16
     learnt
    1.16
     lessons
    1.10
     lesson
    1.10
     taught
    0.97
    learn
    0.97
     Teach
    0.94
    ĸļ
    0.90
    Activations Density 0.039%

    No Known Activations