© 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 24576
    9. 8-RES_FS24576-JB
    11. 8496
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of things appearing or happening unexpectedly

    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
    125
    +0.13
    0.6%
    726
    +0.11
    0.5%
    719
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.13
    0.03
    322
    +0.11
    0.02
    553
    +0.09
    0.02
    Negative Logits
    arine
    -0.82
     CLSID
    -0.77
    mens
    -0.76
    jah
    -0.68
    UME
    -0.66
    "]=>
    -0.65
    sis
    -0.64
    ritical
    -0.63
    aga
    -0.62
    apy
    -0.62
    POSITIVE LOGITS
     spontaneously
    1.02
     prominently
    0.89
     banners
    0.89
     everywhere
    0.87
    river
    0.79
     balloons
    0.78
     unexpectedly
    0.76
     anywhere
    0.75
    Interstitial
    0.74
     billboards
    0.72
    Activations Density 0.052%

    No Known Activations