© 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. 24032
    Prev
    Next
    INDEX
    Explanations

    phrases related to preparation or planning for an event or action

    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
    723
    +0.09
    0.4%
    338
    +0.09
    0.4%
    269
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.09
    0.02
    761
    +0.09
    0.02
    646
    +0.09
    0.02
    Negative Logits
     thereof
    -0.70
     froze
    -0.69
     Mub
    -0.68
    aca
    -0.66
     Approximately
    -0.64
     Advertisement
    -0.63
    SPONSORED
    -0.63
     âĸĪ
    -0.62
    croft
    -0.61
     incidentally
    -0.61
    POSITIVE LOGITS
     preparations
    0.85
     plans
    0.81
     Phase
    0.77
    Ready
    0.75
    ãĤĭ
    0.72
     stages
    0.71
     contingency
    0.71
     bullish
    0.70
     ambitions
    0.70
     momentum
    0.70
    Activations Density 0.060%

    No Known Activations