© 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. 19438
    Prev
    Next
    INDEX
    Explanations

    words related to medical treatments using engineered immune cells

    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
    610
    +0.14
    0.6%
    694
    +0.10
    0.4%
    223
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.14
    0.03
    362
    +0.10
    0.04
    223
    +0.09
    0.03
    Negative Logits
    soDeliveryDate
    -0.98
    HUD
    -0.95
    Weather
    -0.88
     trave
    -0.87
    conom
    -0.84
    displayText
    -0.82
    iquette
    -0.80
     enthusi
    -0.79
    soType
    -0.79
    aution
    -0.78
    POSITIVE LOGITS
     DNA
    1.46
     genes
    1.44
     embryos
    1.44
     proteins
    1.42
     genomes
    1.37
     chromosome
    1.35
     genetically
    1.34
     genome
    1.32
     genomic
    1.31
     gene
    1.29
    Activations Density 0.274%

    No Known Activations