© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5881
    Prev
    Next
    INDEX
    Explanations

    sentences related to healthcare and government policies, particularly concerning topics like mental health, healthcare services, and regulations

    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
    79
    +0.11
    0.5%
    283
    +0.10
    0.5%
    325
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    79
    +0.11
    0.06
    283
    +0.10
    0.01
    86
    +0.09
    0.05
    Negative Logits
    colored
    -0.81
     traveled
    -0.81
     flavors
    -0.78
     gotten
    -0.77
    GOP
    -0.76
     folks
    -0.76
    imize
    -0.74
    Defense
    -0.74
    center
    -0.74
    avored
    -0.73
    POSITIVE LOGITS
     £
    1.28
     recognise
    1.27
     programme
    1.25
     recognised
    1.23
     organisation
    1.22
     programmes
    1.18
     licence
    1.17
     maths
    1.17
     favour
    1.16
     mould
    1.14
    Activations Density 1.603%

    No Known Activations