© 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. 12221
    Prev
    Next
    INDEX
    Explanations

    references to online interaction marks, such as bookmarks and sharing options

    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
    726
    +0.10
    0.4%
    497
    +0.10
    0.4%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    396
    +0.10
    0.01
    373
    +0.10
    -0.00
    592
    +0.09
    0.01
    Negative Logits
    agan
    -0.74
    apor
    -0.72
     Galile
    -0.66
    ocally
    -0.64
    odka
    -0.64
    rera
    -0.63
    orem
    -0.63
     dancers
    -0.62
     Lauder
    -0.62
     negotiators
    -0.62
    POSITIVE LOGITS
    hyde
    0.90
    tenance
    0.88
    mark
    0.73
    ing
    0.73
    /-
    0.72
    imensional
    0.72
    link
    0.71
    lishing
    0.71
    eer
    0.71
    itors
    0.69
    Activations Density 0.016%

    No Known Activations