© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 6850
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to laws and suits

    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
    674
    +0.14
    0.6%
    103
    +0.14
    0.6%
    407
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.14
    0.04
    678
    +0.14
    0.04
    238
    +0.11
    0.04
    Negative Logits
    ãĤ´ãĥ³
    -0.73
     defe
    -0.64
     Sovere
    -0.62
     Vi
    -0.60
    FI
    -0.56
     Chao
    -0.55
    BE
    -0.54
     DeL
    -0.53
     Bridge
    -0.53
    ONSORED
    -0.53
    POSITIVE LOGITS
     apiece
    1.51
     worth
    1.01
    poons
    0.99
     per
    0.97
    each
    0.96
    illion
    0.92
     each
    0.92
    dozen
    0.91
    secut
    0.88
    plus
    0.86
    Activations Density 0.349%

    No Known Activations