© 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. 1417
    Prev
    Next
    INDEX
    Explanations

    words related to technology news and announcements

    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
    424
    +0.09
    0.4%
    412
    +0.09
    0.4%
    305
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.09
    0.05
    752
    +0.09
    0.05
    359
    +0.09
    0.04
    Negative Logits
    etheless
    -0.79
     hybrids
    -0.77
     aliases
    -0.77
    acters
    -0.73
    vae
    -0.73
     subcontract
    -0.72
     regulars
    -0.69
     verbs
    -0.66
     fingerprints
    -0.65
     depended
    -0.65
    POSITIVE LOGITS
     Expo
    1.18
     Exhibition
    1.12
     Festival
    1.11
    Fest
    1.10
     Summit
    1.05
     Pavilion
    1.04
     Auditor
    1.02
     Awards
    1.02
     Theatre
    1.01
     Hotel
    1.00
    Activations Density 0.319%

    No Known Activations