© 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. 12124
    Prev
    Next
    INDEX
    Explanations

    adjectives related to emotions and opinions

    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
    718
    +0.11
    0.5%
    674
    +0.10
    0.5%
    377
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.11
    0.08
    55
    +0.10
    0.08
    102
    +0.10
    0.08
    Negative Logits
    arta
    -0.81
    ologies
    -0.76
     VIDEOS
    -0.74
    =-=-=-=-=-=-=-=-
    -0.74
    mare
    -0.70
    Dialogue
    -0.69
     newsletters
    -0.68
    Nation
    -0.68
     sucks
    -0.66
     =================================
    -0.65
    POSITIVE LOGITS
     unsuccessful
    1.06
     instrumental
    1.01
     initially
    0.96
     originally
    0.95
     conceived
    0.94
     successful
    0.93
     able
    0.84
     born
    0.83
     intended
    0.82
     unexpected
    0.81
    Activations Density 0.371%

    No Known Activations