© 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. 24546
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities involved in various situations, particularly legal or governmental contexts

    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
    578
    +0.13
    0.6%
    659
    +0.12
    0.6%
    767
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    767
    +0.13
    0.04
    659
    +0.12
    0.04
    578
    +0.12
    0.03
    Negative Logits
    ĪĴ
    -0.81
    ãĥĹ
    -0.67
     contagious
    -0.66
     resil
    -0.64
     dish
    -0.61
     juggling
    -0.60
     Yamaha
    -0.59
     Maker
    -0.58
     Tycoon
    -0.57
    Ĥ¬
    -0.56
    POSITIVE LOGITS
    ologne
    1.23
    redits
    1.18
    ursor
    1.16
    oding
    1.15
    rossover
    1.12
    ounters
    1.09
    ategories
    1.08
    rawl
    1.08
    ognitive
    1.07
    ouple
    1.07
    Activations Density 0.044%

    No Known Activations