© 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. 14195
    Prev
    Next
    INDEX
    Explanations

    descriptions of events in a news report related to conflicts and emergencies

    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
    225
    +0.11
    0.5%
    121
    +0.11
    0.5%
    120
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.11
    0.04
    225
    +0.11
    0.04
    79
    +0.10
    0.04
    Negative Logits
     plagiar
    -0.99
     Patent
    -0.91
     patent
    -0.89
     Abram
    -0.76
     shrew
    -0.73
    gom
    -0.72
     Mormonism
    -0.72
     jealousy
    -0.70
     genius
    -0.70
     patents
    -0.69
    POSITIVE LOGITS
     evacuated
    1.50
     evacuation
    1.36
     evac
    1.21
     evacuate
    1.20
     curfew
    1.17
    irens
    1.13
     lockdown
    1.05
     reopened
    0.96
     precaution
    0.95
     barric
    0.94
    Activations Density 0.565%

    No Known Activations