© 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. 7273
    Prev
    Next
    INDEX
    Explanations

    information related to geopolitical conflicts, unrest, government actions, and human rights abuses in different regions

    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
    12
    +0.09
    0.4%
    135
    +0.08
    0.4%
    711
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    488
    +0.09
    0.05
    86
    +0.08
    0.05
    756
    +0.08
    -0.02
    Negative Logits
    NAS
    -0.85
     Whitney
    -0.76
    omorph
    -0.75
     Folder
    -0.73
    nesota
    -0.73
    ository
    -0.73
    reetings
    -0.72
     Assignment
    -0.71
    umbn
    -0.70
    Zip
    -0.70
    POSITIVE LOGITS
     accuse
    1.13
     blamed
    1.05
     accuses
    1.02
     crackdown
    1.00
     separatist
    0.99
     blames
    0.98
     separatists
    0.97
     Nato
    0.96
     rebels
    0.96
     angered
    0.95
    Activations Density 0.884%

    No Known Activations