© 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. 8133
    Prev
    Next
    INDEX
    Explanations

    deforestation-related terms and practices

    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
    481
    +0.16
    0.8%
    756
    +0.16
    0.7%
    35
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    35
    +0.16
    0.04
    529
    +0.16
    0.04
    756
    +0.12
    -0.02
    Negative Logits
    boxing
    -0.80
    verbal
    -0.75
     impuls
    -0.73
    ebin
    -0.72
    FBI
    -0.72
     psychiatrists
    -0.71
     Schumer
    -0.71
     verbal
    -0.71
    umbledore
    -0.71
    Rating
    -0.70
    POSITIVE LOGITS
     vegetation
    1.44
     soils
    1.40
     habitats
    1.39
     irrig
    1.35
     wetlands
    1.34
     habitat
    1.34
     farmland
    1.34
     forests
    1.34
     biodiversity
    1.31
     grazing
    1.29
    Activations Density 0.754%

    No Known Activations