© 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. 19630
    Prev
    Next
    INDEX
    Explanations

    words related to benchmarking and performance testing

    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
    418
    +0.13
    0.6%
    24
    +0.11
    0.5%
    506
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.13
    0.01
    24
    +0.11
    0.01
    288
    +0.11
    0.01
    Negative Logits
     traged
    -0.76
    oho
    -0.75
    Else
    -0.67
    uthor
    -0.67
     incorpor
    -0.65
    NetMessage
    -0.65
     emanc
    -0.64
    ole
    -0.64
    por
    -0.64
    agan
    -0.64
    POSITIVE LOGITS
    mark
    1.03
     benchmark
    1.00
    marks
    1.00
     benchmarks
    0.94
    bench
    0.77
    osterone
    0.77
    ometer
    0.74
    imony
    0.72
     dummy
    0.72
     suite
    0.71
    Activations Density 0.019%

    No Known Activations