© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3346
    Prev
    Next
    INDEX
    Explanations

    instances of dishonesty or deception in a given context

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    150
    +0.12
    0.6%
    213
    +0.10
    0.5%
    310
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    150
    +0.12
    0.04
    608
    +0.10
    0.05
    97
    +0.10
    0.03
    Negative Logits
    Interstitial
    -0.77
    arthy
    -0.69
    nam
    -0.68
    runs
    -0.61
     oak
    -0.60
    lim
    -0.59
     uncontrolled
    -0.59
     unmarked
    -0.59
     formatted
    -0.58
    Ļ½
    -0.56
    POSITIVE LOGITS
     shareholders
    1.04
     regulators
    0.89
     investors
    0.88
     consumers
    0.85
     audiences
    0.84
     us
    0.83
     investigators
    0.82
     creditors
    0.82
     voters
    0.81
     listeners
    0.81
    Activations Density 0.232%

    No Known Activations