© 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. 3315
    Prev
    Next
    INDEX
    Explanations

    mentions of "Twitter" in the text

    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
    582
    +0.13
    0.6%
    167
    +0.13
    0.6%
    128
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.02
    406
    +0.13
    0.02
    582
    +0.11
    0.01
    Negative Logits
     reper
    -0.69
     Kingdoms
    -0.69
    ilitation
    -0.67
    cephal
    -0.64
    aucas
    -0.59
    ournals
    -0.59
     Azerb
    -0.58
    urat
    -0.58
     Sharia
    -0.57
    enses
    -0.57
    POSITIVE LOGITS
    bug
    1.23
    bugs
    1.10
    geist
    1.09
    ing
    0.87
    sburg
    0.87
    bomb
    0.86
    cair
    0.85
    alling
    0.83
    loo
    0.82
    idge
    0.82
    Activations Density 0.044%

    No Known Activations