© 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 12288
    5. 8-RES_FS12288-JB
    6. 10567
    Prev
    Next
    INDEX
    Explanations

    information related to sports events or announcements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    640
    +0.33
    1.6%
    447
    +0.15
    0.7%
    481
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.33
    0.17
    442
    +0.15
    0.14
    107
    +0.12
    0.13
    Negative Logits
     persuasion
    -0.87
     reflex
    -0.86
     equival
    -0.83
     grop
    -0.79
     suppression
    -0.78
     naive
    -0.76
     favor
    -0.76
     favour
    -0.76
     bias
    -0.75
     agon
    -0.75
    POSITIVE LOGITS
    Tickets
    1.58
    Among
    1.54
    RELATED
    1.51
    Meanwhile
    1.48
    Also
    1.48
    Additionally
    1.45
    According
    1.44
    Along
    1.41
    Advertisement
    1.39
    While
    1.39
    Activations Density 0.619%

    No Known Activations