© 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. 8948
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and software development, such as API, jQuery, software, drivers, update, virtual navigation keys, and gestures

    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
    447
    +0.20
    0.9%
    718
    +0.11
    0.5%
    71
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.20
    0.05
    455
    +0.11
    0.05
    86
    +0.11
    0.04
    Negative Logits
     Buster
    -0.73
    ĸļ
    -0.69
     Deadly
    -0.67
     Spoon
    -0.66
    ILA
    -0.66
     Vulcan
    -0.65
     Chimera
    -0.65
     Panda
    -0.65
     Anyway
    -0.65
    ategory
    -0.64
    POSITIVE LOGITS
     prefer
    0.94
     succumbed
    0.93
     mistakenly
    0.92
     aspire
    0.92
     swear
    0.92
     specialize
    0.90
     perished
    0.89
     believe
    0.89
     opted
    0.89
     hesitate
    0.87
    Activations Density 0.184%

    No Known Activations