© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23917
    Prev
    Next
    INDEX
    Explanations

    conjunctions and expressions of simultaneous actions or relationships

    oai_token-act-pair · gpt-4o-miniTriggered 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
    373
    +0.13
    0.6%
    224
    +0.10
    0.5%
    359
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.13
    0.02
    373
    +0.10
    -0.01
    72
    +0.10
    0.02
    Negative Logits
     Merrill
    -0.65
    SourceFile
    -0.61
    omy
    -0.61
    minecraft
    -0.60
     Ludwig
    -0.59
    xual
    -0.58
    aila
    -0.58
     DeV
    -0.56
    olkien
    -0.56
     Donation
    -0.54
    POSITIVE LOGITS
     Tomorrow
    0.88
     Forever
    0.79
    days
    0.76
     2024
    0.76
    ciating
    0.73
     hereafter
    0.73
     tomorrow
    0.73
     2050
    0.72
    thens
    0.71
     2019
    0.71
    Activations Density 0.091%

    No Known Activations