© 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 12288
    9. 8-RES_FS12288-JB
    11. 10508
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreements and concessions between different entities or countries

    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
    447
    +0.14
    0.6%
    224
    +0.13
    0.6%
    288
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.14
    0.04
    224
    +0.13
    0.04
    575
    +0.12
    0.04
    Negative Logits
    asus
    -0.90
    crow
    -0.80
    gun
    -0.71
    station
    -0.71
    psy
    -0.69
     darts
    -0.68
    espie
    -0.67
    stocks
    -0.67
    CTV
    -0.66
    ixel
    -0.66
    POSITIVE LOGITS
     agreements
    1.21
     Agreement
    1.15
     negotiated
    1.14
    reements
    1.14
     agreement
    1.14
     treaties
    1.08
     treaty
    1.06
    breaker
    0.94
    breakers
    0.93
     Treaty
    0.93
    Activations Density 0.103%

    No Known Activations