© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 26614
    Prev
    Next
    INDEX
    Explanations

    mentions of Colombia in various contexts

    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
    288
    +0.17
    0.8%
    481
    +0.15
    0.7%
    447
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.17
    0.01
    288
    +0.15
    0.01
    316
    +0.14
    0.01
    Negative Logits
    oppable
    -0.83
    vity
    -0.80
    lihood
    -0.77
    ŃĶ
    -0.75
    umbnails
    -0.75
    ership
    -0.74
    ELF
    -0.73
    mith
    -0.72
    lopp
    -0.72
    yll
    -0.72
    POSITIVE LOGITS
     Colombia
    0.89
     pes
    0.85
     Peru
    0.83
     Uruguay
    0.83
     cartels
    0.80
     Rican
    0.80
     Rica
    0.79
     Springs
    0.78
     Beans
    0.76
     beans
    0.75
    Activations Density 0.005%

    No Known Activations