© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 1423
    Prev
    Next
    INDEX
    Explanations

    words related to drug trafficking and criminal activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    481
    +0.14
    0.7%
    298
    +0.12
    0.5%
    362
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.14
    0.06
    608
    +0.12
    0.06
    748
    +0.11
    0.03
    Negative Logits
    cules
    -0.82
    æ³
    -0.82
    mates
    -0.79
    framework
    -0.77
    iquette
    -0.76
    æĦ
    -0.75
    mate
    -0.70
    imei
    -0.70
    yssey
    -0.69
    åij
    -0.69
    POSITIVE LOGITS
     suicides
    0.92
     absentee
    0.87
     births
    0.86
     uninsured
    0.86
     homegrown
    0.84
     arrivals
    0.84
     fatalities
    0.82
     violent
    0.80
     casualties
    0.80
     activity
    0.80
    Activations Density 0.418%

    No Known Activations