© 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. 8675
    Prev
    Next
    INDEX
    Explanations

    words related to rules or limitations imposed on a particular group or activity

    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
    575
    +0.11
    0.5%
    447
    +0.11
    0.5%
    497
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.11
    0.02
    417
    +0.11
    0.02
    575
    +0.10
    0.02
    Negative Logits
    mberg
    -0.72
    past
    -0.68
     Zeit
    -0.68
     Generations
    -0.67
    fortune
    -0.65
    uni
    -0.65
    psc
    -0.65
    nexus
    -0.64
    vironment
    -0.64
    ilus
    -0.64
    POSITIVE LOGITS
     imposed
    1.10
     restricting
    1.04
     restricts
    0.95
     restrictions
    0.94
     prohibiting
    0.94
     prohibited
    0.92
     inhib
    0.90
     restriction
    0.87
     enforced
    0.83
     limiting
    0.83
    Activations Density 0.040%

    No Known Activations