© 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. 26594
    Prev
    Next
    INDEX
    Explanations

    terms related to colonialism and its effects

    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
    +0.23
    1.0%
    459
    +0.14
    0.7%
    481
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.23
    0.01
    604
    +0.14
    0.01
    459
    +0.13
    0.01
    Negative Logits
    Downloadha
    -1.06
    TOP
    -0.93
    paces
    -0.77
    kick
    -0.73
    */(
    -0.70
    share
    -0.69
    pace
    -0.69
    match
    -0.69
     Finder
    -0.69
    colo
    -0.68
    POSITIVE LOGITS
     colonial
    0.95
     settlers
    0.88
     sett
    0.88
     Colonial
    0.87
    ization
    0.87
     slavery
    0.86
    ized
    0.83
     outpost
    0.80
    isation
    0.80
     warfare
    0.80
    Activations Density 0.006%

    No Known Activations