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. 873
    Prev
    Next
    INDEX
    Explanations

    terms related to energy production and distribution, particularly focusing on the concept of distributed energy and its advantages such as reliability

    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
    724
    +0.15
    0.7%
    255
    +0.13
    0.6%
    288
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.15
    0.15
    225
    +0.13
    0.13
    288
    +0.12
    0.13
    Negative Logits
    eric
    -0.74
    onal
    -0.72
    ERSON
    -0.69
    roleum
    -0.67
    joining
    -0.67
    reon
    -0.67
    endar
    -0.66
    inis
    -0.65
    yton
    -0.65
    iger
    -0.64
    POSITIVE LOGITS
     assurance
    0.96
    fulness
    0.91
     quot
    0.87
     inherent
    0.85
    iness
    0.84
     theorem
    0.82
     issues
    0.80
    iqueness
    0.80
     ratings
    0.79
     mismatch
    0.78
    Activations Density 1.176%

    No Known Activations