© 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. 19323
    Prev
    Next
    INDEX
    Explanations

    phrases related to relocation or moving

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    608
    +0.15
    0.7%
    723
    +0.12
    0.6%
    123
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.15
    0.05
    104
    +0.12
    0.03
    665
    +0.12
    0.04
    Negative Logits
    ŃĶ
    -0.72
    soever
    -0.72
     hurled
    -0.71
     swayed
    -0.67
    spir
    -0.64
    Ĥª
    -0.64
    IJ
    -0.64
    ¿½
    -0.63
    Words
    -0.62
    ¼
    -0.62
    POSITIVE LOGITS
     accommodate
    0.84
    oult
    0.78
     capitalize
    0.77
     Tycoon
    0.75
     eliminate
    0.75
     Nanto
    0.73
    ggles
    0.72
     grips
    0.70
     Las
    0.69
     ç¥ŀ
    0.68
    Activations Density 0.091%

    No Known Activations