© 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. 45618
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific discoveries and advancements

    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
    373
    +0.11
    0.5%
    7
    +0.11
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    108
    +0.11
    0.03
    38
    +0.11
    0.03
    472
    +0.10
    0.02
    Negative Logits
    iquette
    -1.00
     Restaur
    -0.95
     Rampage
    -0.80
    estate
    -0.79
     Loyal
    -0.76
    iors
    -0.75
    vg
    -0.75
    Exit
    -0.75
    ibur
    -0.74
    ardless
    -0.73
    POSITIVE LOGITS
     scientists
    1.48
     researchers
    1.44
     biologists
    1.39
     scientific
    1.35
     studies
    1.32
     laboratory
    1.28
     physicists
    1.27
     neuroscience
    1.26
     laboratories
    1.26
     theorists
    1.25
    Activations Density 0.308%

    No Known Activations