© 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 24576
    9. 8-RES_FS24576-JB
    11. 11001
    Prev
    Next
    INDEX
    Explanations

    phrases related to discounts and promotions

    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
    579
    +0.14
    0.7%
    592
    +0.13
    0.6%
    688
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    592
    +0.14
    0.04
    579
    +0.13
    0.05
    688
    +0.10
    0.04
    Negative Logits
    polit
    -0.74
     theoret
    -0.73
     landsl
    -0.73
     deposition
    -0.72
     inco
    -0.72
     disson
    -0.71
     scapego
    -0.71
     dissect
    -0.70
     Inspector
    -0.70
     misinterpret
    -0.70
    POSITIVE LOGITS
     discounts
    1.36
     coupon
    1.35
     rebate
    1.28
     coupons
    1.23
     Premium
    1.21
     discount
    1.19
     Discount
    1.16
     subscription
    1.16
     discounted
    1.15
     perks
    1.15
    Activations Density 0.482%

    No Known Activations