© 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 24576
    9. 8-RES_FS24576-JB
    11. 1923
    Prev
    Next
    INDEX
    Explanations

    references to seeds and planting

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    459
    +0.17
    0.8%
    642
    +0.13
    0.6%
    148
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.17
    0.02
    642
    +0.13
    0.01
    473
    +0.10
    0.01
    Negative Logits
     mathemat
    -0.73
    zzi
    -0.71
     seiz
    -0.69
    quished
    -0.68
    pload
    -0.67
    ĵĺ
    -0.65
    ĺħ
    -0.65
    oreal
    -0.64
     behav
    -0.64
    paio
    -0.64
    POSITIVE LOGITS
    lings
    1.25
    ling
    1.05
    orf
    1.02
    lein
    0.91
    belt
    0.85
     ger
    0.84
    seed
    0.83
     planted
    0.82
    bank
    0.81
     Seeds
    0.81
    Activations Density 0.018%

    No Known Activations