© 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 EvalsExportsinterp-engineNEWAPI 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. 45438
    Prev
    Next
    INDEX
    Explanations

    phrases related to pre-orders

    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
    0
    +0.12
    0.6%
    651
    +0.10
    0.5%
    566
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    +0.12
    0.03
    433
    +0.10
    0.03
    653
    +0.10
    0.03
    Negative Logits
    loo
    -0.74
     Heights
    -0.67
    ĸļ
    -0.65
     Ago
    -0.64
    hetti
    -0.64
     Shack
    -0.62
    IBLE
    -0.60
     Soup
    -0.60
     Zamb
    -0.60
     Nig
    -0.60
    POSITIVE LOGITS
    requisites
    1.30
    req
    1.18
    orders
    1.17
    occup
    1.13
    fecture
    1.11
    order
    1.08
    ceed
    1.08
    release
    1.07
    lude
    1.06
    selected
    1.05
    Activations Density 0.013%

    No Known Activations