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

    Neuronpedia

    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. 9690
    Prev
    Next
    INDEX
    Explanations

    news organizations and political figures

    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
    692
    +0.10
    0.4%
    373
    +0.09
    0.4%
    185
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.10
    0.05
    267
    +0.09
    0.05
    475
    +0.09
    0.05
    Negative Logits
    interstitial
    -0.74
    tumblr
    -0.70
    ;;;;;;;;;;;;
    -0.69
    $$$$
    -0.68
    range
    -0.67
    scl
    -0.66
    venge
    -0.66
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.64
     Confederacy
    -0.64
    erva
    -0.63
    POSITIVE LOGITS
     correspondent
    1.06
     understands
    1.00
     reporter
    0.98
     reports
    0.96
     reported
    0.90
     investigates
    0.89
     contacted
    0.89
     Investigative
    0.89
     reporters
    0.88
     interviewed
    0.87
    Activations Density 0.153%

    No Known Activations