© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8021
    Prev
    Next
    INDEX
    Explanations

    information related to news articles, events, and locations 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
    348
    +0.10
    0.5%
    31
    +0.10
    0.4%
    435
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    268
    +0.10
    0.01
    557
    +0.10
    0.01
    586
    +0.09
    0.01
    Negative Logits
    worldly
    -0.81
    oplan
    -0.77
    etheless
    -0.76
    omnia
    -0.76
    riched
    -0.72
    ften
    -0.69
    ngth
    -0.69
    kaya
    -0.68
    Ĥ¬
    -0.68
    ĪĴ
    -0.68
    POSITIVE LOGITS
     Courtesy
    0.83
     Sioux
    0.75
     Highlights
    0.71
     toggle
    0.70
    SHARE
    0.67
     caption
    0.67
     Wait
    0.66
     Transcript
    0.65
     IMAGES
    0.64
     taxpayer
    0.64
    Activations Density 0.005%

    No Known Activations