© 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 49152
    9. 8-RES_FS49152-JB
    11. 45650
    Prev
    Next
    INDEX
    Explanations

    terms related to a rapid increase or significant rise in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    464
    +0.12
    0.6%
    203
    +0.10
    0.4%
    75
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.12
    0.01
    464
    +0.10
    0.01
    555
    +0.09
    0.01
    Negative Logits
     Luxem
    -0.78
    DEP
    -0.70
    ļéĨĴ
    -0.66
    REDACTED
    -0.65
    ++++
    -0.63
    asper
    -0.62
    SG
    -0.62
    ItemTracker
    -0.61
     Fas
    -0.61
     pleading
    -0.60
    POSITIVE LOGITS
    oric
    1.45
     mete
    0.97
    ors
    0.95
    omy
    0.89
    ewater
    0.83
    iation
    0.81
    ilon
    0.81
    rics
    0.80
    ogram
    0.79
    omic
    0.79
    Activations Density 0.006%

    No Known Activations