© 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. 1421
    Prev
    Next
    INDEX
    Explanations

    phrases related to political conflict and government actions

    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
    352
    +0.11
    0.5%
    575
    +0.11
    0.5%
    360
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.11
    0.09
    23
    +0.11
    0.07
    103
    +0.09
    0.07
    Negative Logits
    anwhile
    -0.69
     scatter
    -0.65
     exhib
    -0.63
    creen
    -0.63
     Tradable
    -0.62
    EStream
    -0.62
     Send
    -0.61
     Mov
    -0.61
     Agric
    -0.61
     Incarn
    -0.60
    POSITIVE LOGITS
    ¬
    1.13
    ¡
    1.07
    Ĵ
    1.04
    ľ
    1.02
    º
    1.01
    ¦
    1.00
    ĸ
    0.99
    į
    0.98
    ı
    0.97
    ¼
    0.97
    Activations Density 0.165%

    No Known Activations