Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 40040
    Prev
    Next
    INDEX
    Explanations

    phrases indicating subjective experiences and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    226
    +0.10
    0.5%
    609
    +0.09
    0.4%
    43
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    45
    +0.10
    0.01
    226
    +0.09
    0.01
    566
    +0.09
    0.01
    Negative Logits
    module
    -0.64
     moreover
    -0.63
    task
    -0.62
    bath
    -0.62
    asus
    -0.60
    quad
    -0.60
    iband
    -0.59
    Furthermore
    -0.58
     Mund
    -0.58
    ationally
    -0.58
    POSITIVE LOGITS
     spared
    0.67
     somew
    0.64
     insured
    0.64
     avoided
    0.62
     appe
    0.62
    cknowled
    0.61
    tta
    0.61
     acknowledgement
    0.60
    veyard
    0.60
    riott
    0.59
    Activations Density 0.063%

    No Known Activations