© 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. 18475
    Prev
    Next
    INDEX
    Explanations

    verbs in the present participle form ending in "-ing."

    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
    526
    +0.13
    0.6%
    116
    +0.11
    0.5%
    34
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.01
    156
    +0.11
    0.01
    526
    +0.10
    0.00
    Negative Logits
    velength
    -0.77
    isable
    -0.68
    esthetic
    -0.65
    asonable
    -0.63
    WAYS
    -0.62
     Rouge
    -0.62
    ndra
    -0.61
    fx
    -0.61
    RED
    -0.61
    llular
    -0.60
    POSITIVE LOGITS
    buster
    0.98
    neck
    0.94
     bust
    0.89
    enegger
    0.89
    lar
    0.85
    s
    0.84
    ing
    0.81
    les
    0.81
    sch
    0.81
    busters
    0.80
    Activations Density 0.019%

    No Known Activations