© 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. 3904
    Prev
    Next
    INDEX
    Explanations

    adjective-noun pairs indicating positive attributes or capabilities

    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
    373
    +0.31
    1.5%
    481
    +0.12
    0.6%
    105
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.31
    0.04
    404
    +0.12
    0.03
    711
    +0.10
    0.02
    Negative Logits
    etsk
    -0.70
    Rush
    -0.68
    Secure
    -0.67
    sung
    -0.60
    ï¸ı
    -0.60
     Khal
    -0.58
     Reyes
    -0.58
     McCoy
    -0.57
     Watson
    -0.56
    rador
    -0.56
    POSITIVE LOGITS
     extraord
    0.67
     tendencies
    0.67
     basis
    0.65
     equivalent
    0.65
     equivalents
    0.63
     indu
    0.63
     behav
    0.62
     prowess
    0.60
     instincts
    0.60
    ALLY
    0.59
    Activations Density 0.208%

    No Known Activations