© 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. 8870
    Prev
    Next
    INDEX
    Explanations

    requests to watch videos

    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
    738
    +0.10
    0.5%
    426
    +0.10
    0.5%
    396
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    426
    +0.10
    0.02
    738
    +0.10
    0.02
    396
    +0.09
    0.02
    Negative Logits
    ctrl
    -0.80
    bably
    -0.80
    phi
    -0.69
    cffffcc
    -0.67
    currency
    -0.67
     wound
    -0.66
    ylum
    -0.65
    ayers
    -0.63
    ãĥ´
    -0.62
    cffff
    -0.61
    POSITIVE LOGITS
    tower
    1.32
    dog
    1.13
    dogs
    1.04
    ing
    0.98
     clips
    0.88
     Dogs
    0.83
     videos
    0.83
     Watching
    0.82
    ers
    0.79
    points
    0.78
    Activations Density 0.022%

    No Known Activations