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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 1646
    Prev
    Next
    INDEX
    Explanations

    phrases related to peace and conflict resolution

    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
    208
    +0.13
    0.6%
    575
    +0.11
    0.5%
    459
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.11
    575
    +0.11
    0.08
    271
    +0.11
    0.05
    Negative Logits
    åĭ
    -0.68
     ultras
    -0.66
    inx
    -0.65
    hyper
    -0.64
    GPU
    -0.63
     Heller
    -0.62
     plagiar
    -0.62
     blat
    -0.61
    drivers
    -0.61
    azeera
    -0.60
    POSITIVE LOGITS
    hearted
    0.97
    keeping
    0.91
    peace
    0.90
    ably
    0.90
    keeper
    0.89
    liness
    0.88
     breeze
    0.88
    keepers
    0.86
    haven
    0.86
     tranquil
    0.83
    Activations Density 1.414%

    No Known Activations