© 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. 45500
    Prev
    Next
    INDEX
    Explanations

    information related to instances of violence, crime, and legal matters

    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
    447
    +0.19
    0.9%
    481
    +0.14
    0.7%
    358
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.19
    0.05
    575
    +0.14
    0.06
    288
    +0.11
    0.07
    Negative Logits
    pires
    -0.82
    itates
    -0.55
     ceases
    -0.55
     sleeps
    -0.54
     relies
    -0.52
    itiz
    -0.51
     likes
    -0.51
     guiIcon
    -0.50
    bara
    -0.49
     grows
    -0.49
    POSITIVE LOGITS
     respectively
    1.81
     apiece
    1.40
     respective
    0.96
     themselves
    0.93
     together
    0.88
     collectively
    0.79
    *.
    0.76
     jointly
    0.74
     whereas
    0.72
    .
    0.71
    Activations Density 0.557%

    No Known Activations