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 49152
    5. 8-RES_FS49152-JB
    6. 43271
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistical data and ratios

    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
    393
    +0.09
    0.4%
    43
    +0.09
    0.4%
    104
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    150
    +0.09
    0.02
    409
    +0.09
    0.02
    131
    +0.09
    0.02
    Negative Logits
    artifacts
    -0.67
    BUG
    -0.65
    mingham
    -0.65
    ayn
    -0.64
     smells
    -0.64
    andal
    -0.63
    dream
    -0.62
    videos
    -0.62
    pict
    -0.61
    hend
    -0.61
    POSITIVE LOGITS
     GDP
    1.16
     total
    0.92
     GN
    0.77
     average
    0.74
     gross
    0.73
     Gross
    0.72
     normal
    0.70
    Total
    0.70
     overall
    0.69
    obar
    0.66
    Activations Density 0.047%

    No Known Activations