© 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. 15617
    Prev
    Next
    INDEX
    Explanations

    phrases related to optimization or improvement

    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
    465
    +0.12
    0.6%
    145
    +0.11
    0.5%
    276
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    465
    +0.12
    0.01
    450
    +0.11
    0.01
    276
    +0.11
    0.01
    Negative Logits
    ãĥĨãĤ£
    -0.75
    ptives
    -0.73
    UGH
    -0.73
    INESS
    -0.65
    ILY
    -0.62
     havoc
    -0.62
    FORE
    -0.62
    Madison
    -0.61
     withd
    -0.60
    ELD
    -0.60
    POSITIVE LOGITS
    imum
    1.21
    imal
    1.14
    imus
    1.00
    ician
    0.94
    icians
    0.94
    ima
    0.91
    ometry
    0.88
    uary
    0.86
    ics
    0.85
    aye
    0.83
    Activations Density 0.009%

    No Known Activations