© 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. 11905
    Prev
    Next
    INDEX
    Explanations

    dates and locations mentioned in news articles

    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
    373
    +0.22
    1.1%
    430
    +0.12
    0.6%
    350
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.22
    -0.01
    430
    +0.12
    0.04
    530
    +0.08
    0.03
    Negative Logits
     Boo
    -0.55
     incompet
    -0.54
     Wee
    -0.53
     curls
    -0.52
     gore
    -0.51
     Grow
    -0.51
    dule
    -0.51
     gib
    -0.50
     Kirin
    -0.50
     Geh
    -0.49
    POSITIVE LOGITS
    MEN
    0.63
    WASHINGTON
    0.62
    âĶĢ
    0.62
    SHARE
    0.61
    impl
    0.60
     BALL
    0.60
    CONT
    0.60
    atform
    0.59
    wikipedia
    0.57
    arbon
    0.57
    Activations Density 0.097%

    No Known Activations