© 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. 22806
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to legal and governmental processes

    oai_token-act-pair · gpt-4o-miniTriggered 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
    481
    +0.45
    2.3%
    447
    +0.22
    1.1%
    288
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.45
    0.10
    481
    +0.22
    0.08
    540
    +0.09
    0.07
    Negative Logits
     thous
    -0.63
     funky
    -0.61
     proble
    -0.56
    ;;;;;;;;
    -0.56
    anooga
    -0.55
     thirsty
    -0.54
     Damn
    -0.54
     trendy
    -0.54
     endif
    -0.54
     thirst
    -0.54
    POSITIVE LOGITS
     waivers
    0.72
     veto
    0.71
     ballots
    0.69
     ceremony
    0.67
    arial
    0.66
    atories
    0.64
     rating
    0.64
    heet
    0.63
     standings
    0.63
     auction
    0.63
    Activations Density 0.660%

    No Known Activations