Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23577
    Prev
    Next
    INDEX
    Explanations

    references to military operations involving drones

    oai_token-act-pair · gpt-4o-miniTriggered 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
    154
    +0.10
    0.5%
    17
    +0.10
    0.4%
    474
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.07
    127
    +0.10
    0.05
    494
    +0.09
    0.06
    Negative Logits
    Assistant
    -0.82
    CEO
    -0.76
    APD
    -0.74
    Customer
    -0.74
    ONY
    -0.73
     exec
    -0.71
    pkg
    -0.71
    Consumer
    -0.70
    aughs
    -0.68
    Chair
    -0.68
    POSITIVE LOGITS
     coastline
    1.34
     northern
    1.30
     southwestern
    1.30
     inland
    1.26
     coastal
    1.25
     southern
    1.24
     rivers
    1.22
     northeastern
    1.22
     northwestern
    1.22
     southeastern
    1.22
    Activations Density 0.597%

    No Known Activations