© 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. 20199
    Prev
    Next
    INDEX
    Explanations

    text related to computer software and programming

    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
    507
    +0.10
    0.5%
    58
    +0.10
    0.5%
    447
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.10
    0.05
    665
    +0.10
    0.05
    611
    +0.10
    0.05
    Negative Logits
    backer
    -0.78
    fal
    -0.70
    united
    -0.68
    mania
    -0.67
    Mania
    -0.67
    ilings
    -0.65
    INGTON
    -0.64
     Advent
    -0.63
    league
    -0.63
     Study
    -0.63
    POSITIVE LOGITS
     automatically
    1.07
     detects
    0.89
     dynamically
    0.89
     incoming
    0.86
     fingerprints
    0.81
     detect
    0.77
     autonom
    0.77
     inputs
    0.76
     instantaneous
    0.76
     milliseconds
    0.75
    Activations Density 0.371%

    No Known Activations