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

    Neuronpedia

    Jacobian LensNEW
    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 24576
    9. 8-RES_FS24576-JB
    11. 10960
    Prev
    Next
    INDEX
    Explanations

    comparisons involving the word "more."

    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
    132
    +0.13
    0.6%
    94
    +0.11
    0.5%
    389
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    389
    +0.13
    0.06
    647
    +0.11
    0.05
    132
    +0.11
    0.05
    Negative Logits
    xtap
    -0.81
    heid
    -0.72
    atan
    -0.71
    rosis
    -0.69
    ideos
    -0.67
    etimes
    -0.66
    DragonMagazine
    -0.65
    æ©
    -0.64
    oes
    -0.64
    ipment
    -0.63
    POSITIVE LOGITS
     than
    1.42
     likely
    1.06
     complicated
    1.05
     importantly
    1.01
     inclined
    1.00
     efficient
    0.99
    than
    0.99
     suited
    0.96
     expensive
    0.94
     nuanced
    0.93
    Activations Density 0.092%

    No Known Activations