© 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 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. 12352
    Prev
    Next
    INDEX
    Explanations

    government-related terms

    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
    756
    +0.13
    0.6%
    92
    +0.11
    0.5%
    241
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.13
    0.04
    258
    +0.11
    0.04
    288
    +0.10
    0.05
    Negative Logits
    potion
    -0.71
    CHAT
    -0.68
    morning
    -0.66
    Recommend
    -0.64
    selection
    -0.64
     Kara
    -0.63
     pier
    -0.62
     Factor
    -0.61
    Channel
    -0.61
    Bay
    -0.61
    POSITIVE LOGITS
    hips
    1.15
    chool
    1.06
    hip
    1.01
    agascar
    0.87
    mith
    0.80
    ystem
    0.80
     governments
    0.80
     collide
    0.80
     empires
    0.78
     alike
    0.78
    Activations Density 0.184%

    No Known Activations