© 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. 14666
    Prev
    Next
    INDEX
    Explanations

    references to political conflicts and negotiations, especially focusing on specific historical events and their implications

    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
    92
    +0.11
    0.5%
    387
    +0.11
    0.5%
    514
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.11
    0.13
    352
    +0.11
    0.14
    514
    +0.10
    0.13
    Negative Logits
     Franch
    -0.69
     Guinness
    -0.64
     nail
    -0.64
     Rochester
    -0.63
     Slov
    -0.62
     Postal
    -0.62
     scatter
    -0.62
     Springer
    -0.61
     Miche
    -0.61
     Mov
    -0.60
    POSITIVE LOGITS
    Ŀ
    1.38
    ¡
    1.21
    °
    1.13
    ľ
    1.09
    ¦
    1.08
    ¤
    1.07
    Ń
    1.05
    ¿
    1.04
    Ł
    1.02
    ŀ
    1.02
    Activations Density 0.311%

    No Known Activations