© 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 1536
    9. 8-RES_FS1536-JB
    11. 1156
    Prev
    Next
    INDEX
    Explanations

    word stems related to the concept of maternal or matriarchal roles in society

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    651
    +0.15
    0.7%
    283
    +0.13
    0.6%
    420
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.14
    232
    +0.13
    0.10
    651
    +0.10
    0.10
    Negative Logits
    ¥ŀ
    -0.76
    ĺħ
    -0.73
    ADE
    -0.71
    ĨĴ
    -0.65
    士
    -0.64
     obser
    -0.62
    SPONSORED
    -0.62
    aughter
    -0.59
     precedent
    -0.59
    OUS
    -0.59
    POSITIVE LOGITS
    ting
    1.73
    ches
    1.46
    rix
    1.44
    ters
    1.40
    terson
    1.36
    ty
    1.32
    hered
    1.31
    tered
    1.28
    hetically
    1.26
    rition
    1.24
    Activations Density 2.479%

    No Known Activations