© 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. 15602
    Prev
    Next
    INDEX
    Explanations

    the word roots "re-", indicating a concept of doing something again or differently

    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
    706
    +0.12
    0.5%
    710
    +0.11
    0.5%
    503
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    706
    +0.12
    0.03
    710
    +0.11
    0.03
    670
    +0.10
    0.03
    Negative Logits
    BuyableInstoreAndOnline
    -0.84
    DragonMagazine
    -0.80
     Pebble
    -0.72
     Beir
    -0.71
     Nest
    -0.67
     Eck
    -0.67
     Berm
    -0.64
    ONES
    -0.64
     Zamb
    -0.64
     Sammy
    -0.63
    POSITIVE LOGITS
    porter
    1.23
    venge
    1.18
    asons
    1.13
    ached
    1.11
    actor
    1.11
    ceiver
    1.09
    becca
    1.09
    versible
    1.08
    cover
    1.07
    venue
    1.06
    Activations Density 0.038%

    No Known Activations