© 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. 19621
    Prev
    Next
    INDEX
    Explanations

    words related to telecommunication and technology companies

    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
    288
    +0.12
    0.5%
    481
    +0.11
    0.5%
    484
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.02
    484
    +0.11
    0.02
    538
    +0.11
    0.01
    Negative Logits
    ilts
    -0.89
    auder
    -0.74
    lain
    -0.74
    orian
    -0.71
    uate
    -0.71
    uating
    -0.71
    iewicz
    -0.70
     Frie
    -0.69
    herty
    -0.68
    udo
    -0.68
    POSITIVE LOGITS
     Regulatory
    1.05
     operators
    0.94
     providers
    0.93
     companies
    0.91
     compan
    0.90
     sector
    0.89
     provider
    0.88
     giants
    0.87
     subscriber
    0.87
     subscribers
    0.85
    Activations Density 0.035%

    No Known Activations