© 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. 23018
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a speaker's emphasis or opinion in a discourse

    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
    596
    +0.12
    0.5%
    389
    +0.10
    0.4%
    501
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    596
    +0.12
    0.02
    389
    +0.10
    0.02
    297
    +0.09
    0.01
    Negative Logits
    MpServer
    -0.76
    interstitial
    -0.75
    olved
    -0.74
    ille
    -0.69
    /
    -0.69
    SourceFile
    -0.67
    ILLE
    -0.66
    mage
    -0.66
    âĵĺ
    -0.65
    Mesh
    -0.65
    POSITIVE LOGITS
     yeah
    1.22
     honestly
    1.07
     imagine
    0.97
     maybe
    0.94
     wow
    0.94
     why
    0.93
     hey
    0.92
     sure
    0.88
     uh
    0.87
     WHAT
    0.87
    Activations Density 0.039%

    No Known Activations