© 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. 24170
    Prev
    Next
    INDEX
    Explanations

    instances of the word "decide" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    134
    +0.12
    0.6%
    45
    +0.12
    0.5%
    7
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.12
    0.03
    134
    +0.12
    0.03
    665
    +0.11
    0.03
    Negative Logits
    oil
    -0.84
    ngth
    -0.75
    oof
    -0.72
    atha
    -0.72
    acements
    -0.71
    athi
    -0.70
    ubric
    -0.70
    href
    -0.69
    oing
    -0.66
    amon
    -0.65
    POSITIVE LOGITS
     whether
    1.06
     unanimously
    0.82
     how
    0.75
     deciding
    0.74
    whether
    0.74
     decide
    0.74
     decisions
    0.72
     unilaterally
    0.70
     upon
    0.69
     decisively
    0.68
    Activations Density 0.043%

    No Known Activations