© 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. 8016
    Prev
    Next
    INDEX
    Explanations

    phrases related to commitment and dedication

    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
    665
    +0.11
    0.5%
    608
    +0.10
    0.5%
    74
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.11
    0.03
    665
    +0.10
    0.03
    385
    +0.10
    0.03
    Negative Logits
    DragonMagazine
    -1.24
    æĺ
    -0.77
    ults
    -0.75
    lords
    -0.72
    llo
    -0.71
    soDeliveryDate
    -0.71
    igmatic
    -0.69
    aurus
    -0.67
    ipples
    -0.66
    acements
    -0.65
    POSITIVE LOGITS
     preserving
    1.15
     maintaining
    1.03
     secrecy
    1.02
     excellence
    1.01
     keeping
    0.97
     ensuring
    0.97
     achieving
    0.97
     improving
    0.96
     upholding
    0.96
     protecting
    0.91
    Activations Density 0.084%

    No Known Activations