Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 716
    Prev
    Next
    INDEX
    Explanations

    phrases related to international affairs, political matters, and human rights issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    288
    +0.13
    0.6%
    554
    +0.11
    0.5%
    267
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.13
    0.10
    288
    +0.11
    0.10
    67
    +0.10
    0.09
    Negative Logits
    veyard
    -0.86
    uden
    -0.79
    HOU
    -0.77
    gger
    -0.76
    cht
    -0.74
    chers
    -0.74
    yard
    -0.73
    lington
    -0.73
    atto
    -0.72
    astern
    -0.72
    POSITIVE LOGITS
     affairs
    0.96
     treaties
    0.94
     warming
    0.92
    isation
    0.91
     relations
    0.88
     Affairs
    0.87
    ization
    0.86
     treaty
    0.84
     espionage
    0.83
     diplomatic
    0.82
    Activations Density 1.079%

    No Known Activations