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. 11598
    Prev
    Next
    INDEX
    Explanations

    political and military-related textual content

    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
    639
    +0.10
    0.5%
    698
    +0.09
    0.4%
    727
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.10
    0.03
    698
    +0.09
    0.03
    707
    +0.08
    0.03
    Negative Logits
    ipop
    -0.69
    hou
    -0.68
    ysis
    -0.67
    esan
    -0.64
    oshop
    -0.62
    rences
    -0.61
     cons
    -0.61
    ...]
    -0.61
    â̦]
    -0.59
     butterflies
    -0.59
    POSITIVE LOGITS
    _-
    0.95
    avanaugh
    0.73
    yes
    0.72
    ITS
    0.71
    âĸº
    0.70
    sil
    0.70
    ->
    0.70
    tags
    0.68
    natureconservancy
    0.68
    meaning
    0.68
    Activations Density 0.049%

    No Known Activations