© 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. 24574
    Prev
    Next
    INDEX
    Explanations

    instances of the word "we" and related variations indicating a collective perspective or action

    oai_token-act-pair · gpt-4o-miniTriggered 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
    167
    +0.11
    0.5%
    610
    +0.11
    0.5%
    551
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.11
    0.06
    354
    +0.11
    0.06
    173
    +0.10
    0.05
    Negative Logits
    forms
    -0.71
     Organizations
    -0.59
    âĢ¢âĢ¢
    -0.57
     Oprah
    -0.56
     Authority
    -0.56
    Times
    -0.56
     Crusade
    -0.55
    whel
    -0.55
     Rarity
    -0.55
     AIDS
    -0.54
    POSITIVE LOGITS
    're
    1.09
    ighed
    1.08
    arers
    1.06
     assume
    1.02
    've
    1.00
     ourselves
    0.96
    athered
    0.96
    aning
    0.94
    'll
    0.94
    eding
    0.93
    Activations Density 0.138%

    No Known Activations