© 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 49152
    9. 8-RES_FS49152-JB
    11. 25966
    Prev
    Next
    INDEX
    Explanations

    actions and events related to legal and political processes

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    481
    +0.11
    0.5%
    306
    +0.11
    0.5%
    764
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.11
    0.04
    761
    +0.11
    0.03
    206
    +0.10
    0.02
    Negative Logits
    ãĤ©
    -0.73
    çĶ°
    -0.71
    faced
    -0.67
     Audi
    -0.64
    DragonMagazine
    -0.64
    advertisement
    -0.64
    ãĥ´
    -0.64
    not
    -0.63
     testament
    -0.63
     introducing
    -0.62
    POSITIVE LOGITS
     anymore
    0.99
     altogether
    0.97
     undue
    0.78
     nor
    0.74
     whatsoever
    0.74
     any
    0.71
    BuyableInstoreAndOnline
    0.69
     violent
    0.69
     harmful
    0.68
     entirely
    0.67
    Activations Density 0.096%

    No Known Activations