© 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. 45583
    Prev
    Next
    INDEX
    Explanations

    terms related to friendliness and sustainability

    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
    447
    +0.13
    0.6%
    248
    +0.11
    0.5%
    408
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    248
    +0.13
    0.01
    408
    +0.11
    0.02
    329
    +0.11
    0.01
    Negative Logits
    staking
    -0.87
    krit
    -0.77
    adder
    -0.75
    inus
    -0.75
    dust
    -0.74
    foreseen
    -0.74
    actionDate
    -0.74
    quist
    -0.73
    verbal
    -0.73
    munition
    -0.72
    POSITIVE LOGITS
     environment
    0.88
     alternatives
    0.86
    lihood
    0.84
     environments
    0.82
     atmosphere
    0.80
     alternative
    0.80
     policies
    0.78
     solutions
    0.74
     style
    0.74
     workplaces
    0.73
    Activations Density 0.027%

    No Known Activations