© 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. 7809
    Prev
    Next
    INDEX
    Explanations

    words related to riots or controversies in political or organizational contexts

    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
    26
    +0.11
    0.5%
    99
    +0.10
    0.5%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    26
    +0.11
    0.02
    659
    +0.10
    0.01
    603
    +0.10
    0.01
    Negative Logits
    ¯¯¯¯¯¯¯¯
    -0.68
     mileage
    -0.66
    ¯¯¯¯
    -0.64
    âĸ¬âĸ¬
    -0.64
     Abs
    -0.60
     cath
    -0.58
     Masquerade
    -0.57
     corrid
    -0.57
     Monstrous
    -0.57
     Caldwell
    -0.56
    POSITIVE LOGITS
    dates
    1.49
    stairs
    1.21
    olicy
    1.14
    dating
    1.10
    edia
    1.09
    rising
    1.08
    odcast
    1.08
    rint
    1.07
    inion
    1.07
    grades
    1.07
    Activations Density 0.022%

    No Known Activations