© 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. 24172
    Prev
    Next
    INDEX
    Explanations

    words associated with light and illumination

    oai_token-act-pair · gpt-4o-miniTriggered 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
    99
    +0.14
    0.6%
    383
    +0.12
    0.6%
    586
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.02
    99
    +0.12
    0.02
    578
    +0.12
    0.01
    Negative Logits
    ãĥ¯ãĥ³
    -0.70
     Daly
    -0.67
    Lay
    -0.66
    ordan
    -0.65
    Bound
    -0.63
    TAIN
    -0.60
    ighed
    -0.60
    ryu
    -0.60
    ĥ
    -0.59
    zanne
    -0.59
    POSITIVE LOGITS
     brighter
    1.00
     glow
    0.99
     bulbs
    0.97
     brightly
    0.96
    ingly
    0.96
    orescence
    0.95
     orbs
    0.94
    lights
    0.92
     violet
    0.91
     lights
    0.88
    Activations Density 0.047%

    No Known Activations