© 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. 18852
    Prev
    Next
    INDEX
    Explanations

    technical and programming terms and concepts

    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
    447
    +0.23
    1.1%
    373
    +0.13
    0.6%
    688
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.23
    0.05
    308
    +0.13
    0.03
    6
    +0.10
    0.04
    Negative Logits
    kefeller
    -0.81
    plet
    -0.69
    leigh
    -0.67
    daq
    -0.65
    mere
    -0.65
    qus
    -0.64
    redo
    -0.63
    ischer
    -0.63
    Ð
    -0.60
    ibo
    -0.59
    POSITIVE LOGITS
     Whenever
    0.92
     Suppose
    0.89
     Whilst
    0.88
     Sometimes
    0.88
    ccording
    0.86
     Although
    0.86
     Firstly
    0.86
     While
    0.85
     Currently
    0.84
     Allows
    0.84
    Activations Density 0.189%

    No Known Activations