© 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. 15621
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to combat or physical conflict

    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
    85
    +0.12
    0.6%
    247
    +0.12
    0.5%
    496
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    85
    +0.12
    0.04
    531
    +0.12
    0.03
    492
    +0.10
    0.03
    Negative Logits
    ographical
    -0.79
     Seym
    -0.75
    essage
    -0.69
    pps
    -0.69
    dfx
    -0.68
    uras
    -0.68
    acher
    -0.67
    ajo
    -0.66
    OGR
    -0.65
    æĺ¯
    -0.65
    POSITIVE LOGITS
     against
    1.11
    fighting
    1.04
    fights
    0.96
    fight
    0.95
    fighters
    0.87
     alongside
    0.86
     valiant
    0.85
     raged
    0.84
     fighting
    0.80
     waged
    0.80
    Activations Density 0.039%

    No Known Activations