© 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. 19719
    Prev
    Next
    INDEX
    Explanations

    the word "basing" in various contexts

    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
    549
    +0.15
    0.7%
    218
    +0.11
    0.5%
    421
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    549
    +0.15
    0.01
    421
    +0.11
    0.01
    326
    +0.10
    0.01
    Negative Logits
     Oaks
    -0.67
     Toll
    -0.56
     Rollins
    -0.56
    WIND
    -0.56
    hood
    -0.55
     conscience
    -0.55
    theless
    -0.55
    WORK
    -0.54
     Goods
    -0.54
     flair
    -0.54
    POSITIVE LOGITS
    sembly
    1.04
    ements
    1.00
    emen
    0.98
    cule
    0.95
    estation
    0.94
    idi
    0.89
    ility
    0.88
    uit
    0.86
    imet
    0.85
    ename
    0.84
    Activations Density 0.015%

    No Known Activations