© 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. 22044
    Prev
    Next
    INDEX
    Explanations

    keywords related to environmental impacts, particularly concerning peatlands and climate change

    oai_token-act-pair · gpt-4o-miniTriggered 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
    537
    +0.14
    0.6%
    529
    +0.11
    0.5%
    570
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.06
    67
    +0.11
    0.05
    314
    +0.11
    0.00
    Negative Logits
     Comedy
    -0.80
    HAEL
    -0.79
     witty
    -0.78
     reps
    -0.76
     translator
    -0.75
     Smile
    -0.75
     DeV
    -0.74
     Vanity
    -0.73
     plagiar
    -0.72
     persona
    -0.72
    POSITIVE LOGITS
    forestation
    1.14
     glaciers
    1.05
     vegetation
    1.01
    ewater
    0.99
    carbon
    0.98
    climate
    0.97
     reservoirs
    0.97
     habitats
    0.96
    cycl
    0.94
     rivers
    0.94
    Activations Density 0.320%

    No Known Activations