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 6144
    5. 8-RES_FS6144-JB
    6. 5363
    Prev
    Next
    INDEX
    Explanations

    data points and related data sources

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    167
    +0.12
    0.6%
    288
    +0.11
    0.5%
    698
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    698
    +0.12
    0.05
    439
    +0.11
    0.04
    653
    +0.11
    0.04
    Negative Logits
    ModLoader
    -0.99
    ovie
    -0.76
    lain
    -0.74
     Oath
    -0.71
     Palestin
    -0.70
     Aven
    -0.66
    ouston
    -0.65
     4090
    -0.65
    Ĥª
    -0.64
     Ascend
    -0.63
    POSITIVE LOGITS
    flow
    1.07
     analytics
    0.98
     collection
    0.94
    iologist
    0.94
     recorder
    0.92
     collected
    0.91
    frame
    0.90
    flows
    0.88
     visualization
    0.85
     gathered
    0.81
    Activations Density 0.157%

    No Known Activations