© 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. 7247
    Prev
    Next
    INDEX
    Explanations

    information related to political conflicts and military operations

    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
    102
    +0.19
    0.9%
    314
    +0.17
    0.8%
    160
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.19
    0.05
    124
    +0.17
    0.03
    648
    +0.10
    0.03
    Negative Logits
     Brus
    -0.86
     Bam
    -0.77
     Led
    -0.74
     Barron
    -0.73
     Zup
    -0.71
     Royale
    -0.71
     Grill
    -0.71
     Maze
    -0.70
     rooft
    -0.70
     Butt
    -0.68
    POSITIVE LOGITS
    existent
    1.69
    profit
    1.50
    union
    1.27
    linear
    1.26
    functional
    1.26
    partisan
    1.24
    governmental
    1.24
    violent
    1.23
    zero
    1.23
    inter
    1.22
    Activations Density 0.033%

    No Known Activations