© 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. 8529
    Prev
    Next
    INDEX
    Explanations

    information related to organized contests or competitions

    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
    314
    +0.10
    0.5%
    512
    +0.09
    0.4%
    316
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.02
    507
    +0.09
    0.03
    260
    +0.09
    0.03
    Negative Logits
    rame
    -0.66
     widening
    -0.65
     wiping
    -0.63
     destro
    -0.63
     weakened
    -0.62
     dash
    -0.61
     forcefully
    -0.61
     reapp
    -0.60
    ¥ŀ
    -0.60
     centrif
    -0.60
    POSITIVE LOGITS
    292
    0.88
    96
    0.88
    355
    0.85
    808
    0.85
    31
    0.85
    86
    0.85
    293
    0.85
    66
    0.84
    88
    0.84
    89
    0.84
    Activations Density 0.071%

    No Known Activations