© 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 49152
    5. 8-RES_FS49152-JB
    6. 37519
    Prev
    Next
    INDEX
    Explanations

    variations of names in different languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    265
    +0.12
    0.5%
    759
    +0.11
    0.5%
    393
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    164
    +0.12
    0.03
    265
    +0.11
    0.03
    497
    +0.11
    0.02
    Negative Logits
    Hours
    -0.88
    Technology
    -0.87
    Experience
    -0.87
    Media
    -0.86
    Reward
    -0.86
     Experience
    -0.85
     Voters
    -0.85
    Own
    -0.85
    Government
    -0.84
    Fans
    -0.83
    POSITIVE LOGITS
     etc
    1.13
     nas
    1.11
     coh
    1.07
     aust
    1.00
     ka
    1.00
     sor
    0.99
     mac
    0.97
     ak
    0.95
     carbohyd
    0.94
     py
    0.93
    Activations Density 0.095%

    No Known Activations