© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 26613
    Prev
    Next
    INDEX
    Explanations

    mentions of Russia and related geographic or political 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
    67
    +0.10
    0.5%
    200
    +0.10
    0.4%
    54
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.10
    0.03
    200
    +0.10
    0.03
    54
    +0.10
    0.03
    Negative Logits
    eme
    -0.75
    ointed
    -0.70
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.68
    Mess
    -0.68
    sworth
    -0.67
    ////////
    -0.66
    ients
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.64
    onso
    -0.64
     Berm
    -0.63
    POSITIVE LOGITS
     annexed
    1.09
     Today
    0.94
    borg
    0.87
     Federation
    0.84
    ski
    0.79
    kaya
    0.77
     Tonight
    0.75
    sky
    0.73
    akia
    0.73
     invaded
    0.72
    Activations Density 0.020%

    No Known Activations