© 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. 10071
    Prev
    Next
    INDEX
    Explanations

    mentions of valuable items or collections

    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
    288
    +0.12
    0.6%
    326
    +0.10
    0.5%
    263
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.01
    288
    +0.10
    0.01
    40
    +0.10
    0.01
    Negative Logits
    SPA
    -0.72
     provisional
    -0.64
    slow
    -0.62
     Organic
    -0.61
    erate
    -0.61
     Karin
    -0.60
    TPPStreamerBot
    -0.59
    ECA
    -0.59
     intermittent
    -0.58
    mable
    -0.58
    POSITIVE LOGITS
     trove
    1.67
     chests
    0.96
    collection
    0.94
     treasures
    0.93
     treasure
    0.91
     hoard
    0.89
     stash
    0.86
    abilia
    0.86
     riches
    0.85
    asures
    0.84
    Activations Density 0.020%

    No Known Activations