© 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. 19474
    Prev
    Next
    INDEX
    Explanations

    news related to military and defense activities, as well as mentions of specific locations and names

    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
    299
    +0.12
    0.5%
    248
    +0.10
    0.5%
    118
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    299
    +0.12
    0.05
    659
    +0.10
    0.04
    107
    +0.10
    0.03
    Negative Logits
    advertisement
    -0.65
     berth
    -0.58
    ufact
    -0.57
    interrupted
    -0.57
    tesy
    -0.57
     Grayson
    -0.56
     ASIC
    -0.56
     takeoff
    -0.56
     obscurity
    -0.54
    mouth
    -0.54
    POSITIVE LOGITS
    士
    0.81
    Ó
    0.73
    imaru
    0.73
    ovi
    0.72
    opic
    0.71
    ope
    0.71
    owski
    0.69
    etry
    0.68
    а
    0.66
    ivas
    0.66
    Activations Density 0.175%

    No Known Activations