© 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. 3933
    Prev
    Next
    INDEX
    Explanations

    words related to accomplishments and achievements

    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
    690
    +0.12
    0.6%
    272
    +0.10
    0.5%
    168
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.12
    0.02
    651
    +0.10
    0.02
    724
    +0.10
    0.02
    Negative Logits
     cart
    -0.72
    pheus
    -0.72
    creen
    -0.69
    essel
    -0.69
    zhou
    -0.65
    zhen
    -0.65
    istani
    -0.64
    cart
    -0.64
    AFTA
    -0.64
    SG
    -0.63
    POSITIVE LOGITS
     breaker
    1.01
    breaking
    0.93
     Breaker
    0.86
     record
    0.81
    breakers
    0.78
     holder
    0.75
    keeping
    0.73
    erity
    0.73
    ords
    0.69
    breaker
    0.69
    Activations Density 0.021%

    No Known Activations