© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 26790
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly in the context of data or statistics

    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
    71
    +0.14
    0.6%
    153
    +0.13
    0.6%
    253
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.14
    0.02
    310
    +0.13
    0.02
    289
    +0.12
    0.01
    Negative Logits
    achus
    -0.73
    mble
    -0.72
    BOOK
    -0.71
    nesday
    -0.70
    purpose
    -0.68
    uran
    -0.68
     compr
    -0.67
    uler
    -0.66
    igham
    -0.64
     tiss
    -0.64
    POSITIVE LOGITS
     ILCS
    1.07
    00
    0.97
    328
    0.84
    «ĺ
    0.83
    lav
    0.80
    mph
    0.79
    317
    0.77
    440
    0.76
    ¢
    0.75
     cents
    0.75
    Activations Density 0.028%

    No Known Activations