© 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. 635
    Prev
    Next
    INDEX
    Explanations

    phrases related to government actions and regulations

    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
    288
    +0.13
    0.6%
    488
    +0.13
    0.6%
    496
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    488
    +0.13
    0.06
    146
    +0.13
    0.05
    617
    +0.11
    0.04
    Negative Logits
     Ancest
    -0.69
    Rank
    -0.68
     Blazing
    -0.68
     Klu
    -0.67
    ritch
    -0.66
     Loop
    -0.66
     Locations
    -0.65
     Sic
    -0.65
    CONT
    -0.64
    avery
    -0.64
    POSITIVE LOGITS
     ministers
    0.94
     shutdown
    0.93
     agencies
    0.91
     coffers
    0.90
     departments
    0.88
     ministries
    0.88
     officials
    0.87
     decree
    0.87
    wide
    0.86
     planners
    0.84
    Activations Density 0.096%

    No Known Activations