© 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 EvalsExportsinterp-engineNEWAPI 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. 4120
    Prev
    Next
    INDEX
    Explanations

    political and legal terms, especially related to actions and events involving governmental 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
    272
    +0.10
    0.5%
    561
    +0.10
    0.5%
    567
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    523
    +0.10
    0.04
    259
    +0.10
    0.03
    567
    +0.10
    0.03
    Negative Logits
     partName
    -0.70
     Frie
    -0.70
     yours
    -0.67
     Puzzle
    -0.66
     Hilbert
    -0.66
     unwittingly
    -0.64
    Eva
    -0.64
     fab
    -0.63
     Fortune
    -0.63
     stumble
    -0.63
    POSITIVE LOGITS
     moratorium
    0.94
     boycott
    0.93
     decriminal
    0.86
     abolition
    0.84
     reconsider
    0.83
     intervention
    0.82
     reforms
    0.81
     retribution
    0.80
     deportation
    0.79
     neutrality
    0.79
    Activations Density 0.360%

    No Known Activations