© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7739
    Prev
    Next
    INDEX
    Explanations

    government-related and law enforcement terms

    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
    314
    +0.10
    0.4%
    68
    +0.09
    0.4%
    79
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.05
    115
    +0.09
    0.05
    453
    +0.09
    0.04
    Negative Logits
    acket
    -0.77
    imum
    -0.71
    imus
    -0.68
    thens
    -0.67
    jon
    -0.66
    ousse
    -0.65
    iom
    -0.64
    lio
    -0.64
    ylum
    -0.63
    adobe
    -0.63
    POSITIVE LOGITS
     alike
    1.61
     sectors
    1.17
     perspectives
    1.13
     versions
    1.06
     contexts
    1.03
     environments
    1.03
     spheres
    1.03
     industries
    1.00
     communities
    1.00
     viewpoints
    0.98
    Activations Density 0.203%

    No Known Activations