© 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. 16220
    Prev
    Next
    INDEX
    Explanations

    positive reviews of a product, particularly focusing on aspects like fast shipping, perfect packaging, good quality, and customer satisfaction

    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
    480
    +0.42
    2.1%
    326
    +0.09
    0.4%
    167
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.42
    0.01
    266
    +0.09
    0.08
    326
    +0.09
    0.08
    Negative Logits
     invoking
    -0.70
    onomous
    -0.68
     advers
    -0.66
     governance
    -0.64
     truce
    -0.63
    calling
    -0.63
     disrupting
    -0.63
     speeches
    -0.63
     invoked
    -0.63
     presiding
    -0.62
    POSITIVE LOGITS
     packaging
    1.16
     shipped
    1.13
     shipment
    1.13
     manufacturer
    1.11
     handmade
    1.11
     Warranty
    1.11
     Manufacturer
    1.09
     warranty
    1.09
     sold
    1.09
     accessories
    1.05
    Activations Density 1.000%

    No Known Activations