© 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. 1687
    Prev
    Next
    INDEX
    Explanations

    the word 'per' or variations thereof

    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
    314
    +0.10
    0.4%
    169
    +0.09
    0.4%
    583
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    120
    +0.10
    0.03
    583
    +0.09
    0.03
    467
    +0.09
    0.03
    Negative Logits
     GOODMAN
    -0.76
    enegger
    -0.70
     shortened
    -0.67
    ForgeModLoader
    -0.66
    MpServer
    -0.64
    ARDIS
    -0.63
     Bonds
    -0.63
     pneum
    -0.60
    å¦
    -0.59
     Fargo
    -0.59
    POSITIVE LOGITS
     capita
    1.35
    tains
    1.32
    malink
    1.24
    tained
    1.10
    missive
    1.09
    tain
    1.08
    chance
    1.05
    ishable
    1.04
    severe
    1.04
    verting
    1.04
    Activations Density 0.037%

    No Known Activations