© 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. 19516
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters and patent infringement

    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
    447
    +0.12
    0.6%
    496
    +0.12
    0.6%
    679
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.12
    0.01
    263
    +0.12
    0.01
    316
    +0.12
    0.01
    Negative Logits
    ilde
    -0.66
     Anthrop
    -0.63
     opio
    -0.63
    negie
    -0.61
    nexus
    -0.61
    adi
    -0.59
    night
    -0.59
    hall
    -0.59
    ilts
    -0.58
    ruff
    -0.58
    POSITIVE LOGITS
     infringement
    1.05
     infring
    1.00
     infringing
    0.93
    yrights
    0.87
    yright
    0.83
    ulent
    0.72
    ements
    0.71
    enced
    0.71
    threat
    0.68
     notices
    0.68
    Activations Density 0.020%

    No Known Activations