© 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 24576
    9. 8-RES_FS24576-JB
    11. 9369
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues and policies, particularly focusing on drug-related topics

    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
    373
    +0.10
    0.5%
    226
    +0.10
    0.5%
    671
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    226
    +0.10
    0.02
    311
    +0.10
    0.01
    150
    +0.10
    0.01
    Negative Logits
    gian
    -0.84
    rete
    -0.83
    OGR
    -0.80
    RECT
    -0.79
    nces
    -0.77
    VP
    -0.76
    gaard
    -0.75
    SourceFile
    -0.75
    MpServer
    -0.73
    ringe
    -0.72
    POSITIVE LOGITS
     Drugs
    0.92
     terror
    0.91
     drugs
    0.87
     terrorism
    0.87
     Terror
    0.86
     opioids
    0.79
     Poverty
    0.73
     behalf
    0.72
     poverty
    0.72
     Terrorism
    0.70
    Activations Density 0.046%

    No Known Activations