© 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. 37346
    Prev
    Next
    INDEX
    Explanations

    references to military and geopolitical threats

    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
    756
    +0.15
    0.7%
    314
    +0.12
    0.6%
    742
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.15
    -0.01
    262
    +0.12
    0.02
    86
    +0.11
    0.03
    Negative Logits
     anecd
    -0.79
     goof
    -0.77
     Craigslist
    -0.77
     oddly
    -0.76
     AOL
    -0.74
     weird
    -0.70
     stumbled
    -0.69
     chatting
    -0.69
     geek
    -0.68
     homebrew
    -0.68
    POSITIVE LOGITS
     ceasefire
    0.96
     humanitarian
    0.86
     peaceful
    0.86
     Treaty
    0.85
    xit
    0.85
    Peace
    0.84
     sovereignty
    0.83
    ilateral
    0.83
     cessation
    0.83
    soever
    0.81
    Activations Density 0.427%

    No Known Activations