© 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. 15089
    Prev
    Next
    INDEX
    Explanations

    questions and discussions related to political and philosophical topics

    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
    481
    +0.45
    2.9%
    756
    +0.30
    1.9%
    459
    +0.28
    1.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.45
    -0.01
    459
    +0.30
    0.12
    497
    +0.28
    0.08
    Negative Logits
    ©¶æ
    -0.75
    Ĥİ
    -0.59
    DragonMagazine
    -0.57
    etheless
    -0.56
    è¦ļéĨĴ
    -0.51
    ãĥķãĤ¡
    -0.47
    âĹ¼
    -0.47
    cedented
    -0.46
    iannopoulos
    -0.43
    ãĥĥãĥĪ
    -0.43
    POSITIVE LOGITS
    heid
    0.47
     enlarg
    0.38
     unde
    0.37
     entit
    0.36
     paraph
    0.36
     dynam
    0.36
     unic
    0.35
     elect
    0.35
     isot
    0.35
     sing
    0.34
    Activations Density 3.052%

    No Known Activations