© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 26717
    Prev
    Next
    INDEX
    Explanations

    references to statistical averages and means

    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
    408
    +0.09
    0.4%
    229
    +0.09
    0.4%
    142
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.09
    0.02
    493
    +0.09
    0.02
    445
    +0.09
    0.02
    Negative Logits
    Ü
    -0.94
    ãĤ¦ãĤ¹
    -0.86
    bane
    -0.82
    nuts
    -0.80
    atography
    -0.79
    apons
    -0.79
    olitics
    -0.79
    afort
    -0.78
    pecially
    -0.78
    ãĤ¤ãĥĪ
    -0.77
    POSITIVE LOGITS
     lifespan
    1.08
     amount
    1.04
     hourly
    1.03
     monthly
    1.00
     percentage
    1.00
     number
    0.99
     rate
    0.98
     annual
    0.97
     yearly
    0.95
     duration
    0.94
    Activations Density 0.018%

    No Known Activations