© 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 24576
    9. 8-RES_FS24576-JB
    11. 9468
    Prev
    Next
    INDEX
    Explanations

    phrases related to military or political activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    447
    +0.15
    0.7%
    146
    +0.11
    0.5%
    432
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.15
    0.07
    224
    +0.11
    0.06
    617
    +0.11
    0.05
    Negative Logits
    Pear
    -0.75
     Byrd
    -0.74
     Creek
    -0.71
     Crow
    -0.67
     BYU
    -0.64
    ocene
    -0.63
     Hawth
    -0.62
     UCLA
    -0.62
    bryce
    -0.61
    bucks
    -0.61
    POSITIVE LOGITS
     intervened
    1.06
     reacted
    1.04
     froze
    1.04
     announced
    1.01
     convened
    1.00
     ruled
    0.94
     withdrew
    0.92
     warned
    0.91
     announces
    0.91
     unanimously
    0.91
    Activations Density 0.245%

    No Known Activations