© 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. 41601
    Prev
    Next
    INDEX
    Explanations

    instances of the word "this"

    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
    159
    +0.10
    0.5%
    393
    +0.10
    0.5%
    408
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.10
    0.05
    95
    +0.10
    0.03
    589
    +0.10
    0.03
    Negative Logits
    tones
    -0.88
    oran
    -0.79
    acers
    -0.78
    fed
    -0.77
    bats
    -0.74
    rics
    -0.70
    aughtered
    -0.70
     Roads
    -0.69
    iak
    -0.68
    anches
    -0.67
    POSITIVE LOGITS
     phenomenon
    1.07
     trope
    1.05
     discrepancy
    1.04
     particular
    0.95
     anomaly
    0.90
     happening
    0.90
     happen
    0.88
     limitation
    0.87
     predicament
    0.87
     pecul
    0.86
    Activations Density 0.074%

    No Known Activations