© 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. 9581
    Prev
    Next
    INDEX
    Explanations

    words related to law enforcement and legal matters, particularly focused on investigations and authorities

    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
    481
    +0.11
    0.5%
    762
    +0.11
    0.5%
    447
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.11
    0.03
    509
    +0.11
    0.02
    330
    +0.11
    0.02
    Negative Logits
     Sleeping
    -0.71
    thal
    -0.68
    ces
    -0.65
    ickets
    -0.65
    gets
    -0.65
     Generations
    -0.65
     Spect
    -0.65
    esta
    -0.63
    antam
    -0.62
    opian
    -0.61
    POSITIVE LOGITS
     authorities
    1.02
     agencies
    0.99
     investigating
    0.90
     officials
    0.88
     Authorities
    0.88
     tasked
    0.84
     overseeing
    0.84
     decree
    0.82
     sanctioned
    0.81
     levied
    0.79
    Activations Density 0.032%

    No Known Activations