© 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. 24027
    Prev
    Next
    INDEX
    Explanations

    references to data storage devices, specifically hard drives and USB drives

    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
    611
    +0.10
    0.5%
    220
    +0.10
    0.5%
    61
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    435
    +0.10
    0.01
    678
    +0.10
    0.01
    26
    +0.10
    0.01
    Negative Logits
    rians
    -0.77
    rav
    -0.77
    EY
    -0.75
     Kyr
    -0.73
    ás
    -0.70
    erville
    -0.67
    rian
    -0.66
    ADRA
    -0.66
     Faul
    -0.66
     Pension
    -0.65
    POSITIVE LOGITS
     storage
    1.00
     partitions
    0.99
    disk
    0.96
    storage
    0.87
    caps
    0.85
    pad
    0.85
    Disk
    0.84
    hiba
    0.81
     disks
    0.81
     HDD
    0.79
    Activations Density 0.023%

    No Known Activations