© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9134
    Prev
    Next
    INDEX
    Explanations

    mentions of people, locations, and activities related to gaming and game development, particularly in Japanese contexts

    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
    480
    +0.52
    2.9%
    447
    +0.24
    1.3%
    87
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.52
    0.03
    266
    +0.24
    0.10
    720
    +0.15
    0.06
    Negative Logits
    çīĪ
    -0.69
    adel
    -0.64
    anwhile
    -0.63
    anooga
    -0.61
    _.
    -0.59
    REDACTED
    -0.59
     ensued
    -0.57
    ONSORED
    -0.57
    sequently
    -0.55
    ogether
    -0.53
    POSITIVE LOGITS
     themselves
    0.61
     their
    0.60
     nowadays
    0.59
     certain
    0.56
     excessively
    0.56
     unhealthy
    0.55
    ependent
    0.54
    their
    0.54
     specialize
    0.53
    agonists
    0.52
    Activations Density 1.166%

    No Known Activations