© 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. 18678
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating intensity or degree

    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
    441
    +0.09
    0.4%
    567
    +0.09
    0.4%
    127
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    567
    +0.09
    0.04
    55
    +0.09
    0.04
    441
    +0.09
    0.03
    Negative Logits
     understatement
    -0.73
    orial
    -0.64
    coming
    -0.64
    aptic
    -0.62
    itant
    -0.60
     Borough
    -0.58
    pex
    -0.58
     Bark
    -0.57
    opausal
    -0.57
     Issue
    -0.56
    POSITIVE LOGITS
     differently
    1.05
     smoothly
    0.90
     overboard
    0.87
    into
    0.86
     badly
    0.83
     nicely
    0.81
     slack
    0.81
     closely
    0.80
     poorly
    0.80
     spor
    0.79
    Activations Density 0.102%

    No Known Activations