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 3072
    5. 8-RES_FS3072-JB
    6. 1042
    Prev
    Next
    INDEX
    Explanations

    political and legal terms or concepts

    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
    91
    +0.14
    0.7%
    687
    +0.11
    0.5%
    553
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    91
    +0.14
    0.14
    288
    +0.11
    0.15
    575
    +0.11
    0.12
    Negative Logits
     oneself
    -0.84
    aples
    -0.70
    iably
    -0.63
    acci
    -0.63
    ocene
    -0.63
    isson
    -0.63
     sorts
    -0.61
    skirts
    -0.61
    ometric
    -0.60
    otti
    -0.60
    POSITIVE LOGITS
     counterparts
    0.90
     counterpart
    0.88
     lineup
    0.74
     rivals
    0.74
     selves
    0.72
     woes
    0.72
     namesake
    0.71
    ãĥ¯
    0.71
     predecessors
    0.70
     brethren
    0.69
    Activations Density 2.141%

    No Known Activations