© 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. 15029
    Prev
    Next
    INDEX
    Explanations

    phrases related to attempts or intentions

    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
    70
    +0.11
    0.5%
    282
    +0.10
    0.5%
    459
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.11
    0.05
    282
    +0.10
    0.05
    351
    +0.10
    0.04
    Negative Logits
    dylib
    -0.78
    requisite
    -0.66
    usage
    -0.62
     origin
    -0.58
    effect
    -0.58
    abyte
    -0.57
    spread
    -0.57
    ahu
    -0.57
    inational
    -0.57
    DragonMagazine
    -0.56
    POSITIVE LOGITS
     unsuccessfully
    1.09
     desperately
    1.01
     harder
    0.92
     valiant
    0.87
    reprene
    0.78
     frantically
    0.76
     hard
    0.74
     vain
    0.72
    ioned
    0.70
     to
    0.68
    Activations Density 0.054%

    No Known Activations