© 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. 14709
    Prev
    Next
    INDEX
    Explanations

    adjectives related to physical attributes and characteristics

    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
    362
    +0.15
    0.7%
    36
    +0.10
    0.5%
    234
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.15
    0.06
    669
    +0.10
    0.05
    99
    +0.10
    0.04
    Negative Logits
    OPA
    -0.89
    Monitor
    -0.84
    arthed
    -0.81
    uther
    -0.81
    another
    -0.80
    Journal
    -0.78
    quest
    -0.78
    itizen
    -0.77
    Minor
    -0.76
    eligible
    -0.75
    POSITIVE LOGITS
     nature
    1.19
     exterior
    1.16
     demeanor
    1.13
     attitude
    1.10
    ness
    1.10
     edges
    1.05
     outlook
    1.01
     stature
    1.00
     temperament
    1.00
     interior
    0.99
    Activations Density 0.288%

    No Known Activations