© 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 24576
    9. 8-RES_FS24576-JB
    11. 16717
    Prev
    Next
    INDEX
    Explanations

    references to strategic decision-making and planning in a structured context

    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
    447
    +0.19
    0.9%
    481
    +0.16
    0.8%
    480
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    598
    +0.19
    0.04
    2
    +0.16
    0.04
    393
    +0.12
    0.09
    Negative Logits
    pires
    -0.61
     Contains
    -0.61
    ulates
    -0.60
    yip
    -0.59
    tains
    -0.58
    Allah
    -0.56
    osponsors
    -0.56
     Sharia
    -0.56
    ctuary
    -0.55
     Detect
    -0.55
    POSITIVE LOGITS
     lacked
    1.06
     remained
    1.05
    didn
    1.03
     persisted
    0.99
     reverted
    0.94
     culminated
    0.94
     hindsight
    0.94
     didn
    0.93
     ended
    0.93
     tended
    0.93
    Activations Density 0.924%

    No Known Activations