© 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. 18593
    Prev
    Next
    INDEX
    Explanations

    references to bribery and corruption

    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
    339
    +0.11
    0.5%
    350
    +0.10
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.03
    326
    +0.10
    0.02
    111
    +0.10
    0.02
    Negative Logits
    izen
    -0.74
     Anthem
    -0.73
    stadt
    -0.71
    blance
    -0.70
    ulz
    -0.69
     Balanced
    -0.68
    ãĥ´
    -0.68
    geist
    -0.65
    ouf
    -0.65
    central
    -0.64
    POSITIVE LOGITS
     bribes
    1.01
     extortion
    0.98
     blackmail
    0.97
     lure
    0.87
     bribe
    0.86
     enticing
    0.84
     induce
    0.81
     tempting
    0.79
     tactics
    0.77
     temptation
    0.76
    Activations Density 0.064%

    No Known Activations