© 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 49152
    9. 8-RES_FS49152-JB
    11. 45415
    Prev
    Next
    INDEX
    Explanations

    instances of the word "we" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    551
    +0.13
    0.6%
    481
    +0.11
    0.5%
    685
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.13
    0.07
    551
    +0.11
    0.07
    173
    +0.11
    0.06
    Negative Logits
    cum
    -0.80
    Ore
    -0.65
    Posts
    -0.65
     Eleven
    -0.64
     Grav
    -0.63
     Coco
    -0.62
     Haku
    -0.60
     Clair
    -0.60
    photos
    -0.59
    Appearances
    -0.59
    POSITIVE LOGITS
    're
    1.19
    've
    1.19
    akening
    1.13
    eks
    1.05
     cannot
    1.00
    'll
    0.99
    athered
    0.99
     intend
    0.97
     believe
    0.96
     respectfully
    0.95
    Activations Density 0.144%

    No Known Activations