© 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. 7845
    Prev
    Next
    INDEX
    Explanations

    phrases related to the Takata airbag recalls, particularly mentioning the company and the safety issue

    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
    343
    +0.14
    0.7%
    549
    +0.14
    0.7%
    726
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.14
    0.01
    549
    +0.14
    0.01
    659
    +0.09
    0.01
    Negative Logits
    theless
    -0.74
     guiActiveUnfocused
    -0.68
     prevailing
    -0.67
    ORPG
    -0.67
     Grind
    -0.66
     ILCS
    -0.65
     atmosp
    -0.63
    pherd
    -0.62
    isters
    -0.59
     rid
    -0.59
    POSITIVE LOGITS
    amaru
    1.22
    atsuki
    1.19
    istani
    1.14
    umar
    1.04
    amoto
    0.99
    imura
    0.98
    aka
    0.98
    ata
    0.97
    ushi
    0.96
    ables
    0.96
    Activations Density 0.016%

    No Known Activations