© 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 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. 12642
    Prev
    Next
    INDEX
    Explanations

    references to group dynamics and decision-making within a community

    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
    756
    +0.10
    0.4%
    717
    +0.10
    0.4%
    105
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.10
    0.05
    217
    +0.10
    0.04
    542
    +0.09
    0.04
    Negative Logits
    oris
    -0.65
    ibles
    -0.63
    iq
    -0.60
    ao
    -0.60
    urus
    -0.59
    orum
    -0.59
    Ĭ±
    -0.58
    apses
    -0.58
    Ľ
    -0.56
    iHUD
    -0.56
    POSITIVE LOGITS
     reluctantly
    1.09
     cautiously
    1.03
     willingly
    1.01
     nonetheless
    1.00
     deliberately
    1.00
     intentionally
    0.99
     principally
    0.95
     partly
    0.94
     chiefly
    0.94
     primarily
    0.94
    Activations Density 0.387%

    No Known Activations