© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7077
    Prev
    Next
    INDEX
    Explanations

    phrases related to activism and community organizing, particularly involving standing up for causes and demanding change

    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
    583
    +0.13
    0.6%
    445
    +0.13
    0.6%
    481
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    445
    +0.13
    0.06
    583
    +0.13
    0.04
    526
    +0.12
    -0.01
    Negative Logits
    neau
    -0.78
    Ö¼
    -0.77
     neglig
    -0.75
     hindsight
    -0.74
     psychiatrist
    -0.73
     inexper
    -0.73
    illac
    -0.70
    ©¶æ¥µ
    -0.69
    fixed
    -0.68
     spa
    -0.67
    POSITIVE LOGITS
     solidarity
    1.32
     protest
    1.30
     Protest
    1.27
     boycott
    1.19
     protesting
    1.12
     boycot
    1.06
     Pledge
    1.05
     petition
    1.04
     rallying
    1.03
    against
    1.03
    Activations Density 0.679%

    No Known Activations