© 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. 20162
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives ending in '-ly' or '-ous'

    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
    404
    +0.09
    0.4%
    613
    +0.08
    0.4%
    464
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.09
    0.04
    408
    +0.08
    0.04
    404
    +0.08
    0.03
    Negative Logits
    ernels
    -0.81
    avia
    -0.75
    ©¶æ
    -0.75
    aeper
    -0.75
    ă
    -0.73
    Ė
    -0.73
    ø
    -0.73
    InstoreAndOnline
    -0.72
    socket
    -0.72
    Ě
    -0.72
    POSITIVE LOGITS
    ly
    1.13
    LY
    0.87
     circumstance
    0.83
     proportions
    0.80
    lihood
    0.80
    ness
    0.79
    ity
    0.79
     affair
    0.79
    gery
    0.77
     conco
    0.77
    Activations Density 0.133%

    No Known Activations