© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23859
    Prev
    Next
    INDEX
    Explanations

    instances of the word "arrange" and 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
    546
    +0.11
    0.5%
    717
    +0.11
    0.5%
    684
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    717
    +0.11
    0.01
    665
    +0.11
    0.01
    101
    +0.10
    0.01
    Negative Logits
    lean
    -0.82
    âĵĺ
    -0.80
    ku
    -0.80
    burgh
    -0.69
    pointer
    -0.67
    CVE
    -0.66
    clamation
    -0.65
    Sense
    -0.64
    stone
    -0.62
    Charg
    -0.61
    POSITIVE LOGITS
     arrangements
    1.04
     marriages
    0.97
     arrang
    0.95
     arranging
    0.81
     arranged
    0.80
     Parenthood
    0.76
     arrange
    0.76
    eering
    0.75
     seating
    0.74
     arrangement
    0.74
    Activations Density 0.019%

    No Known Activations