© 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 12288
    9. 8-RES_FS12288-JB
    11. 592
    Prev
    Next
    INDEX
    Explanations

    references to the Serbian community and its related topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    59
    +0.14
    0.6%
    238
    +0.12
    0.6%
    370
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    682
    +0.14
    0.02
    59
    +0.12
    0.02
    628
    +0.12
    0.02
    Negative Logits
    ORN
    -0.78
    enegger
    -0.74
    aneers
    -0.72
    ESCO
    -0.69
    EEK
    -0.67
    reference
    -0.67
    OWS
    -0.66
     Blueprint
    -0.66
    ELS
    -0.64
    WARD
    -0.64
    POSITIVE LOGITS
    geant
    1.29
    pent
    1.13
    otonin
    1.08
    ials
    1.00
    rano
    0.95
    gent
    0.92
    iffs
    0.85
    mons
    0.84
    maid
    0.81
    rha
    0.81
    Activations Density 0.063%

    No Known Activations