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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 1547
    Prev
    Next
    INDEX
    Explanations

    phrases related to social or political activism

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    393
    +0.15
    0.7%
    362
    +0.15
    0.7%
    494
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.15
    0.09
    494
    +0.15
    0.07
    530
    +0.12
    0.06
    Negative Logits
    uala
    -0.71
    fully
    -0.70
    govtrack
    -0.69
    fy
    -0.69
    ful
    -0.68
    raped
    -0.67
    aram
    -0.65
     Luffy
    -0.65
    icho
    -0.65
    fulness
    -0.65
    POSITIVE LOGITS
     globe
    1.45
     periphery
    1.22
     country
    1.12
     edges
    1.07
     perimeter
    0.99
     world
    0.98
     same
    0.98
     entire
    0.97
     continent
    0.97
     coasts
    0.96
    Activations Density 0.558%

    No Known Activations