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 24576
    5. 8-RES_FS24576-JB
    6. 1094
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental impact and processes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    408
    +0.13
    0.6%
    741
    +0.11
    0.5%
    664
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    570
    +0.13
    0.02
    408
    +0.11
    0.06
    362
    +0.10
    0.05
    Negative Logits
    ruary
    -0.84
    ©¶æ
    -0.81
    untu
    -0.76
    ħĭ
    -0.71
    alias
    -0.70
    heses
    -0.70
    nesday
    -0.70
    boxing
    -0.70
     Assass
    -0.70
    feat
    -0.69
    POSITIVE LOGITS
     nutrients
    1.54
     oxygen
    1.45
     energy
    1.35
     fluids
    1.28
     moisture
    1.28
     nitrogen
    1.25
     gases
    1.23
     calcium
    1.22
     electricity
    1.21
     water
    1.19
    Activations Density 0.354%

    No Known Activations