© 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. 1390
    Prev
    Next
    INDEX
    Explanations

    times of day expressed in 12-hour format

    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
    296
    +0.12
    0.6%
    733
    +0.10
    0.5%
    601
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    296
    +0.12
    0.04
    733
    +0.10
    0.03
    262
    +0.10
    0.03
    Negative Logits
     resemb
    -0.69
    govern
    -0.64
     acknowled
    -0.62
     behav
    -0.62
    Bey
    -0.61
    proof
    -0.61
    chie
    -0.61
    products
    -0.60
    designed
    -0.59
    insured
    -0.59
    POSITIVE LOGITS
     EDT
    1.34
     EST
    1.31
     PDT
    1.25
     PST
    1.21
     CET
    1.17
     GMT
    1.15
     CST
    1.13
     BST
    1.10
     ET
    1.10
     UTC
    1.01
    Activations Density 0.034%

    No Known Activations