© 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. 11112
    Prev
    Next
    INDEX
    Explanations

    references to technology, specifically related to robots, software, and internet

    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
    +0.15
    0.7%
    532
    +0.11
    0.5%
    174
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.15
    0.05
    718
    +0.11
    0.04
    532
    +0.10
    0.04
    Negative Logits
    wake
    -0.79
    akens
    -0.79
    oday
    -0.68
     Works
    -0.68
    atur
    -0.64
    redo
    -0.64
     secondly
    -0.63
     tonight
    -0.62
     therein
    -0.61
    ibliography
    -0.60
    POSITIVE LOGITS
     existed
    0.77
     ruled
    0.72
     consisted
    0.71
     thought
    0.68
     unthinkable
    0.68
     regarded
    0.68
     assumed
    0.67
     seemed
    0.67
     relied
    0.67
     doubted
    0.65
    Activations Density 0.456%

    No Known Activations