© 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. 14374
    Prev
    Next
    INDEX
    Explanations

    coordinating conjunctions like "and"

    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
    365
    +0.12
    0.5%
    284
    +0.10
    0.5%
    513
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.12
    0.04
    0
    +0.10
    0.03
    537
    +0.10
    0.04
    Negative Logits
    ETS
    -0.88
    ATS
    -0.77
    IDS
    -0.76
    ÄŁ
    -0.72
     Clouds
    -0.72
    ttes
    -0.72
     Ezek
    -0.71
     Borders
    -0.70
     Boys
    -0.70
     Ratt
    -0.70
    POSITIVE LOGITS
     consequential
    0.97
     productive
    0.96
     efficient
    0.92
     flavorful
    0.91
     durable
    0.90
     economical
    0.89
     inventive
    0.89
     versatile
    0.88
     interconnected
    0.86
     technologically
    0.86
    Activations Density 0.124%

    No Known Activations