© 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 49152
    9. 8-RES_FS49152-JB
    11. 42992
    Prev
    Next
    INDEX
    Explanations

    topics related to retail and shopping experiences

    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
    480
    +0.51
    2.6%
    266
    +0.12
    0.6%
    167
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.51
    0.01
    266
    +0.12
    0.07
    367
    +0.10
    0.05
    Negative Logits
     advers
    -0.75
     theoret
    -0.74
     mathematician
    -0.70
     declass
    -0.70
     pse
    -0.70
    vind
    -0.69
     rewriting
    -0.67
     conjecture
    -0.67
     adversary
    -0.67
     Principle
    -0.66
    POSITIVE LOGITS
     restaurants
    1.29
     supermarkets
    1.22
     customers
    1.19
     storefront
    1.18
     Customers
    1.15
     shops
    1.12
     discounts
    1.11
     retail
    1.11
     shoppers
    1.11
     Restaur
    1.11
    Activations Density 0.672%

    No Known Activations