© 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. 3956
    Prev
    Next
    INDEX
    Explanations

    the word "others."

    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
    459
    +0.12
    0.6%
    19
    +0.10
    0.5%
    389
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.12
    0.03
    300
    +0.10
    0.03
    133
    +0.09
    0.03
    Negative Logits
    -+
    -0.69
    ocracy
    -0.68
    Bound
    -0.67
     Guru
    -0.62
    before
    -0.60
     Donation
    -0.59
     Authorization
    -0.58
     Registration
    -0.58
    )|
    -0.57
    \/
    -0.57
    POSITIVE LOGITS
     succumb
    0.91
     succumbed
    0.84
     prefer
    0.81
     simply
    0.74
     reacts
    0.74
     opted
    0.74
     volunteered
    0.70
     remain
    0.69
     merely
    0.69
     are
    0.68
    Activations Density 0.095%

    No Known Activations