© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 673
    Prev
    Next
    INDEX
    Explanations

    complex and negative statements or descriptions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    480
    +0.29
    1.4%
    314
    +0.14
    0.6%
    157
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.29
    0.09
    650
    +0.14
    0.09
    333
    +0.09
    0.08
    Negative Logits
     incorpor
    -0.76
     condem
    -0.76
     conduc
    -0.72
     synerg
    -0.70
     hemor
    -0.69
     Vaugh
    -0.69
     perspect
    -0.66
     cater
    -0.65
     vulner
    -0.64
     mounts
    -0.64
    POSITIVE LOGITS
    ï¸ı
    1.27
    âĶĢâĶĢ
    1.19
    âĶĢâĶĢâĶĢâĶĢ
    0.97
    §
    0.94
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.90
    âĸł
    0.87
    ×Ķ
    0.86
    _>
    0.85
    à¼
    0.85
    ternity
    0.84
    Activations Density 0.209%

    No Known Activations