© 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. 45741
    Prev
    Next
    INDEX
    Explanations

    conjunctions or phrases that indicate relationships or qualifications within sentences

    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
    393
    +0.12
    0.6%
    761
    +0.11
    0.5%
    60
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.12
    0.05
    109
    +0.11
    0.04
    60
    +0.10
    0.04
    Negative Logits
     Formation
    -0.69
     Thoughts
    -0.66
     wondering
    -0.62
     Biology
    -0.61
     Cards
    -0.60
     Anyway
    -0.59
     moot
    -0.59
     Borough
    -0.58
     guessing
    -0.57
     Founding
    -0.57
    POSITIVE LOGITS
     satisfies
    1.13
     incorporates
    1.02
     resembles
    1.02
     conform
    1.01
     integrates
    0.96
     lasts
    0.94
     fits
    0.92
     reflects
    0.92
     meets
    0.89
     would
    0.88
    Activations Density 0.115%

    No Known Activations