© 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 24576
    9. 8-RES_FS24576-JB
    11. 8649
    Prev
    Next
    INDEX
    Explanations

    historical and political figures and events

    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
    87
    +0.21
    1.0%
    756
    +0.15
    0.7%
    187
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.21
    -0.04
    756
    +0.15
    -0.03
    146
    +0.09
    0.04
    Negative Logits
     emoji
    -0.87
     Xiaomi
    -0.85
     Snapchat
    -0.83
    ï¸ı
    -0.82
    VPN
    -0.81
     veggies
    -0.81
    ðŁ
    -0.80
    Uber
    -0.79
     Lyft
    -0.78
    CNN
    -0.78
    POSITIVE LOGITS
     postwar
    1.05
     1909
    1.01
     1912
    1.00
     1932
    0.98
     1936
    0.98
    oslov
    0.98
     1896
    0.97
     1904
    0.95
     1914
    0.95
     1897
    0.95
    Activations Density 1.461%

    No Known Activations