© 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. 2956
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    480
    +0.26
    1.3%
    447
    +0.24
    1.2%
    640
    +0.20
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.26
    0.12
    640
    +0.24
    0.10
    679
    +0.20
    0.10
    Negative Logits
    idal
    -0.64
    hoe
    -0.63
     contracted
    -0.60
    userc
    -0.58
     condol
    -0.57
    onga
    -0.57
    reet
    -0.57
     birthplace
    -0.57
     commissioned
    -0.57
     curtain
    -0.57
    POSITIVE LOGITS
     Especially
    1.12
     Flavoring
    1.06
     Secondly
    1.04
     Anyway
    1.04
     Firstly
    1.02
     Besides
    0.99
     Thankfully
    0.99
     Whilst
    0.96
     Luckily
    0.96
     Suppose
    0.95
    Activations Density 0.431%

    No Known Activations