© 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 1536
    9. 8-RES_FS1536-JB
    11. 1127
    Prev
    Next
    INDEX
    Explanations

    mentions of humanitarian aid, crises, and related terminology

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    288
    +0.12
    0.5%
    508
    +0.11
    0.5%
    444
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.20
    444
    +0.11
    0.09
    575
    +0.10
    0.12
    Negative Logits
    ounced
    -0.72
    indal
    -0.69
    ellectual
    -0.68
    ģ
    -0.68
    agall
    -0.68
    ularity
    -0.66
    ouver
    -0.65
    amy
    -0.65
    ross
    -0.65
    ounce
    -0.64
    POSITIVE LOGITS
     shelter
    0.97
     Shelter
    0.86
    ilitating
    0.86
     Refugees
    0.85
     SOS
    0.82
     Aid
    0.79
     refugees
    0.79
     shelters
    0.79
     relief
    0.78
     orphans
    0.77
    Activations Density 3.280%

    No Known Activations