© 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. 16829
    Prev
    Next
    INDEX
    Explanations

    mentions of political nationalism and associated concepts

    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
    364
    +0.15
    0.7%
    512
    +0.11
    0.5%
    700
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    512
    +0.15
    0.05
    364
    +0.11
    0.04
    542
    +0.11
    0.04
    Negative Logits
    gov
    -0.72
    bit
    -0.66
    URI
    -0.64
    NB
    -0.63
    learning
    -0.62
    cht
    -0.60
    iverse
    -0.59
    spin
    -0.59
    wait
    -0.59
    TT
    -0.58
    POSITIVE LOGITS
     predecessors
    0.99
     traditionally
    0.94
     previously
    0.94
     hallmark
    0.93
     plague
    0.89
     characterize
    0.87
    senal
    0.87
     normally
    0.86
     formerly
    0.81
     commonly
    0.80
    Activations Density 0.261%

    No Known Activations