© 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 EvalsExportsinterp-engineNEWAPI 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. 22937
    Prev
    Next
    INDEX
    Explanations

    instances of healthcare-related issues and their implications

    oai_token-act-pair · gpt-4o-miniTriggered 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
    87
    +0.20
    0.9%
    590
    +0.11
    0.5%
    670
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    121
    +0.20
    0.06
    31
    +0.11
    0.06
    694
    +0.10
    0.03
    Negative Logits
    olkien
    -0.78
     interstellar
    -0.74
    oÄŁan
    -0.73
     entropy
    -0.72
     inev
    -0.70
     mete
    -0.69
     apocalypse
    -0.69
     treacher
    -0.68
     recognise
    -0.68
    ipedia
    -0.67
    POSITIVE LOGITS
     Sears
    0.85
     Employees
    0.80
     residential
    0.80
     employees
    0.79
     residences
    0.78
     Nationwide
    0.76
     plaintiffs
    0.74
     Riverside
    0.74
     leased
    0.74
     Consumers
    0.74
    Activations Density 0.983%

    No Known Activations