© 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. 8632
    Prev
    Next
    INDEX
    Explanations

    phrases related to allergies, including specific allergic reactions and irritants

    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
    585
    +0.12
    0.5%
    350
    +0.11
    0.5%
    146
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    350
    +0.12
    0.01
    288
    +0.11
    0.02
    195
    +0.10
    0.01
    Negative Logits
    estones
    -0.95
    bourg
    -0.91
    anova
    -0.82
    aji
    -0.72
    estone
    -0.71
    mate
    -0.70
    esan
    -0.69
    fare
    -0.68
    arnaev
    -0.67
    lining
    -0.67
    POSITIVE LOGITS
     sensit
    1.01
     allergic
    1.01
     symptoms
    1.00
     flare
    0.98
     asthma
    0.95
     dermat
    0.94
     allergy
    0.89
     allergies
    0.88
     proble
    0.87
     intoler
    0.84
    Activations Density 0.039%

    No Known Activations