© 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. 12018
    Prev
    Next
    INDEX
    Explanations

    updates and changes made in a software program

    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
    551
    +0.13
    0.6%
    339
    +0.11
    0.5%
    529
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.13
    0.04
    536
    +0.11
    0.03
    304
    +0.10
    0.03
    Negative Logits
    é¾
    -0.72
    efe
    -0.71
    ieu
    -0.68
    achev
    -0.66
     privatization
    -0.65
    str
    -0.64
    phen
    -0.63
    acci
    -0.62
     Divinity
    -0.62
    cos
    -0.60
    POSITIVE LOGITS
    adays
    1.37
    here
    0.96
     correctly
    0.83
     includes
    0.79
     available
    0.78
     include
    0.77
     fully
    0.75
     Available
    0.74
     prioritize
    0.73
     reversible
    0.73
    Activations Density 0.058%

    No Known Activations