© 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. 19522
    Prev
    Next
    INDEX
    Explanations

    content related to screens or display devices

    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
    709
    +0.11
    0.5%
    99
    +0.10
    0.5%
    578
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.11
    0.02
    76
    +0.10
    0.02
    435
    +0.10
    0.02
    Negative Logits
    ortium
    -0.78
    aternal
    -0.78
    doms
    -0.76
     Carnegie
    -0.73
    ghan
    -0.70
    currency
    -0.64
    IGH
    -0.63
    ongo
    -0.63
    aternity
    -0.62
    ETH
    -0.62
    POSITIVE LOGITS
    plays
    1.32
    writers
    1.02
    writer
    1.01
     TVs
    0.97
    tops
    0.97
    printed
    0.96
    grab
    0.96
     screens
    0.96
    writing
    0.95
    caps
    0.94
    Activations Density 0.028%

    No Known Activations