© 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. 7572
    Prev
    Next
    INDEX
    Explanations

    terms related to technical issues or problems encountered with online services

    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
    157
    +0.15
    0.7%
    297
    +0.11
    0.5%
    447
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.15
    0.07
    157
    +0.11
    0.07
    278
    +0.10
    0.05
    Negative Logits
     predecessor
    -0.76
    ONSORED
    -0.68
    xxxx
    -0.68
    lein
    -0.65
    Aw
    -0.64
     candidacy
    -0.63
     Presidency
    -0.63
    achment
    -0.62
     represents
    -0.61
    inventoryQuantity
    -0.61
    POSITIVE LOGITS
     clam
    1.08
    ateurs
    0.95
     understandably
    0.94
     accustomed
    0.92
     increasingly
    0.92
     routinely
    0.91
     alike
    0.88
     generally
    0.88
     everywhere
    0.88
     overwhelmingly
    0.86
    Activations Density 0.303%

    No Known Activations