© 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. 23008
    Prev
    Next
    INDEX
    Explanations

    phrases indicating technology and societal change over time

    oai_token-act-pair · gpt-4o-miniTriggered 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
    203
    +0.12
    0.5%
    715
    +0.11
    0.5%
    34
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    520
    +0.12
    0.04
    203
    +0.11
    0.03
    724
    +0.11
    0.04
    Negative Logits
    ints
    -0.73
     deed
    -0.68
     Clyde
    -0.64
     Yards
    -0.64
     Died
    -0.63
    Residents
    -0.62
     Cosponsors
    -0.62
    cause
    -0.62
     ribs
    -0.62
    KC
    -0.62
    POSITIVE LOGITS
     globalization
    0.92
     democracies
    0.85
     democracy
    0.80
     Orwell
    0.79
     polarized
    0.79
     dystop
    0.75
     dominated
    0.73
     technologically
    0.73
     increasingly
    0.73
     interconnected
    0.73
    Activations Density 0.232%

    No Known Activations