© 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. 22986
    Prev
    Next
    INDEX
    Explanations

    the word "just" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    223
    +0.10
    0.5%
    430
    +0.09
    0.4%
    35
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.10
    0.05
    633
    +0.09
    0.04
    744
    +0.09
    0.04
    Negative Logits
     subsequ
    -0.61
    antis
    -0.61
    agically
    -0.60
     trave
    -0.59
     PLUS
    -0.59
    stress
    -0.59
    risk
    -0.58
    sac
    -0.58
     includ
    -0.58
     destro
    -0.57
    POSITIVE LOGITS
    ifiable
    1.28
    ifications
    1.11
    ifiers
    0.87
    IFIC
    0.86
    ices
    0.86
    ifier
    0.85
     shy
    0.84
    itia
    0.81
    ifi
    0.79
    if
    0.78
    Activations Density 0.068%

    No Known Activations