© 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. 291
    Prev
    Next
    INDEX
    Explanations

    technical information on lithium-ion batteries

    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
    87
    +0.27
    1.4%
    237
    +0.10
    0.5%
    415
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.27
    0.05
    87
    +0.10
    -0.02
    284
    +0.10
    0.04
    Negative Logits
    leck
    -0.68
    itiveness
    -0.55
    ipeg
    -0.54
    tackle
    -0.53
    ĵĺ
    -0.50
    ldon
    -0.48
    illet
    -0.48
    lehem
    -0.48
    pedia
    -0.47
    sterdam
    -0.47
    POSITIVE LOGITS
    ibrary
    0.71
    oxide
    0.62
     Sanct
    0.57
    ãĥĺãĥ©
    0.53
    ioxide
    0.53
    Ń·
    0.52
     dstg
    0.50
    conservancy
    0.48
    ativity
    0.47
    quez
    0.47
    Activations Density 0.701%

    No Known Activations