© 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. 14831
    Prev
    Next
    INDEX
    Explanations

    texts mentioning legal terms and actions

    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
    735
    +0.10
    0.5%
    635
    +0.10
    0.4%
    392
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    735
    +0.10
    0.01
    251
    +0.10
    0.01
    93
    +0.10
    0.01
    Negative Logits
    ĪĴ
    -0.86
    ¥µ
    -0.86
     Skydragon
    -0.69
    EStream
    -0.63
     Unch
    -0.63
     Balk
    -0.61
    nikov
    -0.61
     stink
    -0.60
     Aval
    -0.59
     RTX
    -0.59
    POSITIVE LOGITS
    hester
    1.39
    identally
    1.36
    orporated
    1.34
    idental
    1.27
    idence
    1.21
    arcer
    1.21
    redible
    1.20
    orpor
    1.17
    ipal
    1.14
    redibly
    1.07
    Activations Density 0.010%

    No Known Activations