© 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 EvalsExportsinterp-engineNEWAPI 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. 16620
    Prev
    Next
    INDEX
    Explanations

    technical terms related to networking and server operations

    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
    314
    +0.14
    0.7%
    70
    +0.12
    0.5%
    331
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    331
    +0.14
    0.05
    288
    +0.12
    0.06
    531
    +0.11
    0.04
    Negative Logits
    initions
    -0.77
    HOME
    -0.76
     DeVos
    -0.70
    ortment
    -0.67
    ibraries
    -0.62
     Telephone
    -0.62
     Telescope
    -0.61
    iage
    -0.61
     Wem
    -0.61
    insula
    -0.60
    POSITIVE LOGITS
    worthy
    1.26
    able
    1.17
    isible
    1.03
    arily
    1.01
    ishly
    0.98
    bable
    0.95
    ueless
    0.95
    vable
    0.94
     oriented
    0.94
    ally
    0.94
    Activations Density 0.334%

    No Known Activations