© 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. 2853
    Prev
    Next
    INDEX
    Explanations

    phrases related to construction and weather conditions

    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
    298
    +0.11
    0.5%
    419
    +0.09
    0.4%
    336
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    298
    +0.11
    0.05
    288
    +0.09
    0.08
    417
    +0.09
    0.04
    Negative Logits
    jong
    -0.71
    soDeliveryDate
    -0.65
    REL
    -0.65
    PDATED
    -0.62
    Shares
    -0.62
    ithe
    -0.61
    vale
    -0.61
    Chart
    -0.61
    DAY
    -0.61
    Aid
    -0.60
    POSITIVE LOGITS
     onslaught
    1.29
     pressures
    1.09
     encro
    1.04
     adversity
    1.01
     wrath
    0.95
     whims
    0.94
     intrusion
    0.93
     advers
    0.91
     pitfalls
    0.91
     influx
    0.91
    Activations Density 0.575%

    No Known Activations