© 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. 3632
    Prev
    Next
    INDEX
    Explanations

    Spanish words or phrases

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    373
    +0.12
    0.6%
    27
    +0.12
    0.6%
    221
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    -0.01
    232
    +0.12
    0.04
    284
    +0.11
    0.03
    Negative Logits
    ACTED
    -0.60
     Collider
    -0.59
     PLUS
    -0.59
     adrenaline
    -0.58
     SPD
    -0.58
    CLASSIFIED
    -0.57
    YES
    -0.56
     rigging
    -0.56
    PDATE
    -0.55
     tentacles
    -0.55
    POSITIVE LOGITS
    pling
    1.14
    plings
    0.94
    quer
    0.91
    ashi
    0.84
    amoto
    0.83
    ban
    0.81
    adas
    0.81
    az
    0.81
    amura
    0.80
    aka
    0.80
    Activations Density 0.094%

    No Known Activations