© 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 49152
    9. 8-RES_FS49152-JB
    11. 45644
    Prev
    Next
    INDEX
    Explanations

    words related to the action of rolling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    251
    +0.11
    0.5%
    274
    +0.11
    0.5%
    216
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.11
    0.02
    274
    +0.11
    0.02
    113
    +0.10
    0.02
    Negative Logits
    ILE
    -0.74
    ior
    -0.72
    ãĥ¤
    -0.69
    acters
    -0.67
    orial
    -0.66
    IOR
    -0.65
    bour
    -0.64
    bub
    -0.64
    ãĤ»
    -0.64
    perse
    -0.62
    POSITIVE LOGITS
     downhill
    0.99
     boulder
    0.83
     hills
    0.81
     dice
    0.78
    roll
    0.75
    icking
    0.73
    sheet
    0.73
     oats
    0.73
    sheets
    0.73
     rolling
    0.68
    Activations Density 0.009%

    No Known Activations