© 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. 45734
    Prev
    Next
    INDEX
    Explanations

    the word "both" in various contexts

    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
    373
    +0.14
    0.6%
    106
    +0.11
    0.5%
    744
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    662
    +0.14
    0.03
    744
    +0.11
    0.03
    106
    +0.10
    0.03
    Negative Logits
    xus
    -0.87
    frac
    -0.71
    uez
    -0.71
     Caption
    -0.71
    hibition
    -0.66
    kamp
    -0.65
    ventus
    -0.65
    regation
    -0.62
    ilit
    -0.61
    nce
    -0.61
    POSITIVE LOGITS
     sexes
    1.36
     genders
    1.13
     sides
    1.09
     halves
    0.83
     domestically
    0.83
     verbally
    0.80
     orally
    0.80
     individually
    0.79
     internally
    0.75
     physically
    0.72
    Activations Density 0.033%

    No Known Activations