© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 1278
    Prev
    Next
    INDEX
    Explanations

    mentions of political conflicts and international relations, particularly focusing on the annexation of Crimea

    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
    481
    +0.17
    0.8%
    288
    +0.15
    0.7%
    224
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.02
    57
    +0.15
    0.01
    757
    +0.12
    0.01
    Negative Logits
    tips
    -0.86
    ĸļ
    -0.73
    advertisement
    -0.72
    ISON
    -0.71
    trak
    -0.70
    Hug
    -0.68
    ä
    -0.68
    runner
    -0.67
    cham
    -0.67
    ahime
    -0.67
    POSITIVE LOGITS
     annexation
    1.12
     peninsula
    1.02
     Lumpur
    1.02
     annexed
    0.95
     Peninsula
    0.91
     Tat
    0.88
     Crimea
    0.84
    ignty
    0.79
     Strip
    0.76
     annex
    0.74
    Activations Density 0.021%

    No Known Activations