© 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. 45726
    Prev
    Next
    INDEX
    Explanations

    mentions of Alaska

    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
    57
    +0.14
    0.6%
    288
    +0.14
    0.6%
    481
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.14
    0.01
    224
    +0.14
    0.01
    458
    +0.13
    0.01
    Negative Logits
    eners
    -1.01
    enegger
    -0.85
    colo
    -0.84
    ebook
    -0.74
    advertisement
    -0.73
     Gutenberg
    -0.73
    enance
    -0.69
    etting
    -0.69
    sticks
    -0.69
    ijn
    -0.65
    POSITIVE LOGITS
     Airlines
    1.14
     Anchorage
    1.12
     Springs
    1.10
     Highlands
    0.92
     Native
    0.88
     Pradesh
    0.87
    ansas
    0.85
     Alaska
    0.83
    aska
    0.79
    ħĭ
    0.78
    Activations Density 0.004%

    No Known Activations