© 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 49152
    9. 8-RES_FS49152-JB
    11. 43009
    Prev
    Next
    INDEX
    Explanations

    references to countries, particularly in the context of immigration and refugee-related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    481
    +0.16
    0.7%
    608
    +0.11
    0.5%
    469
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.16
    0.04
    385
    +0.11
    0.04
    584
    +0.10
    0.03
    Negative Logits
    DragonMagazine
    -1.02
    natureconservancy
    -0.90
    Assistant
    -0.84
    motion
    -0.80
    TPPStreamerBot
    -0.80
    iquette
    -0.78
    inen
    -0.77
    ratulations
    -0.76
    olson
    -0.75
    ãĤ¹ãĥĪ
    -0.73
    POSITIVE LOGITS
     abroad
    1.51
     overseas
    1.29
     afar
    1.13
     countries
    1.05
     Syria
    1.04
     Russia
    1.03
     elsewhere
    1.02
     China
    1.02
     Countries
    1.01
     Cuba
    1.00
    Activations Density 0.080%

    No Known Activations