© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 17687
    Prev
    Next
    INDEX
    Explanations

    mentions and discussions related to trees and their impact on the environment and wildlife

    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
    414
    +0.12
    0.5%
    52
    +0.10
    0.5%
    127
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.12
    0.02
    414
    +0.10
    0.02
    52
    +0.10
    0.02
    Negative Logits
    glomer
    -0.81
    arcer
    -0.74
    ersive
    -0.73
    rontal
    -0.72
    oice
    -0.68
     Horowitz
    -0.67
    orical
    -0.65
    iability
    -0.65
    DOS
    -0.64
    ione
    -0.63
    POSITIVE LOGITS
     canopy
    1.21
    frog
    1.08
     trees
    1.04
     stump
    1.01
    beard
    1.00
    Hug
    0.97
    yard
    0.96
     tree
    0.93
     hugging
    0.91
     trunk
    0.90
    Activations Density 0.031%

    No Known Activations