© 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 49152
    9. 8-RES_FS49152-JB
    11. 45569
    Prev
    Next
    INDEX
    Explanations

    terms related to deception or falsehoods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    722
    +0.11
    0.5%
    671
    +0.11
    0.5%
    312
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    324
    +0.11
    0.03
    288
    +0.11
    0.03
    291
    +0.10
    0.03
    Negative Logits
    weeney
    -0.81
    undai
    -0.80
    accompan
    -0.80
    odes
    -0.79
    icts
    -0.77
    laws
    -0.77
    ses
    -0.76
    izont
    -0.74
    ippers
    -0.73
    ographics
    -0.73
    POSITIVE LOGITS
     concoct
    1.13
     invented
    1.02
     perpetrated
    0.91
     unworthy
    0.90
     mir
    0.86
     excuse
    0.83
     gimmick
    0.82
     because
    0.81
     devoid
    0.81
     conceived
    0.80
    Activations Density 0.072%

    No Known Activations