© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 25752
    Prev
    Next
    INDEX
    Explanations

    references to outdated or traditional concepts

    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
    102
    +0.14
    0.7%
    314
    +0.12
    0.6%
    152
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.14
    0.02
    152
    +0.12
    0.02
    493
    +0.10
    0.01
    Negative Logits
    achu
    -0.73
    âķIJ
    -0.70
     DRAG
    -0.70
     Shutterstock
    -0.69
    utterstock
    -0.69
    eele
    -0.69
     latitude
    -0.68
    ï¸ı
    -0.66
     proceeds
    -0.66
     AVG
    -0.66
    POSITIVE LOGITS
    fashioned
    1.36
    style
    1.15
     fashioned
    1.06
    angled
    1.03
    school
    1.03
    sounding
    1.01
    bodied
    1.01
    old
    0.98
    growth
    0.95
    ish
    0.94
    Activations Density 0.017%

    No Known Activations