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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1070
    Prev
    Next
    INDEX
    Explanations

    text related to politics and international relations

    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
    314
    +0.14
    0.6%
    490
    +0.10
    0.5%
    675
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.14
    0.15
    314
    +0.10
    0.03
    48
    +0.10
    0.10
    Negative Logits
     seiz
    -0.74
     myster
    -0.73
     scattering
    -0.71
     sacrific
    -0.69
     Mobil
    -0.64
     Tanz
    -0.63
    achus
    -0.62
     Negro
    -0.61
     notor
    -0.61
     federation
    -0.61
    POSITIVE LOGITS
    ï¸ı
    1.10
    ¯
    0.94
    ttle
    0.88
    s
    0.84
    payer
    0.76
    mental
    0.76
    ti
    0.72
    endif
    0.71
    tal
    0.70
    tarian
    0.70
    Activations Density 1.170%

    No Known Activations