© 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. 43001
    Prev
    Next
    INDEX
    Explanations

    various ways to describe a range or variety of attributes or characteristics

    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
    274
    +0.12
    0.6%
    99
    +0.11
    0.5%
    377
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.12
    0.01
    382
    +0.11
    0.01
    252
    +0.10
    0.01
    Negative Logits
    driving
    -0.66
    verse
    -0.65
    rics
    -0.63
    parent
    -0.63
     syndrome
    -0.62
    win
    -0.62
    anasia
    -0.61
    tha
    -0.58
     bond
    -0.58
    bye
    -0.57
    POSITIVE LOGITS
    Ń·
    0.89
    Ĥª
    0.86
    yip
    0.82
     ranging
    0.79
    ranging
    0.79
     widely
    0.78
     wildly
    0.77
     considerably
    0.76
    ï¸
    0.72
     ranges
    0.71
    Activations Density 0.016%

    No Known Activations