© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 1067
    Prev
    Next
    INDEX
    Explanations

    phrases indicating readiness or transition

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    +0.11
    0.5%
    671
    +0.11
    0.5%
    263
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.11
    0.06
    665
    +0.11
    0.08
    717
    +0.09
    0.05
    Negative Logits
    Rocket
    -0.62
    MJ
    -0.62
    bilt
    -0.59
     Manson
    -0.59
     incoming
    -0.59
    é¾
    -0.58
     Loyal
    -0.57
     Territory
    -0.57
     caption
    -0.57
     Archives
    -0.56
    POSITIVE LOGITS
     blows
    0.97
     fruition
    0.95
     fray
    0.78
     handy
    0.74
     unexpectedly
    0.68
     prominence
    0.68
     grips
    0.68
     leaps
    0.68
     realization
    0.67
    anches
    0.67
    Activations Density 1.995%

    No Known Activations