© 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. 19696
    Prev
    Next
    INDEX
    Explanations

    mentions of women involved in political, social, and cultural contexts

    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
    314
    +0.18
    0.8%
    440
    +0.12
    0.5%
    679
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    440
    +0.18
    0.05
    6
    +0.12
    0.05
    145
    +0.12
    0.04
    Negative Logits
     rall
    -0.81
     purse
    -0.71
     stocking
    -0.70
     enrol
    -0.69
     landscape
    -0.69
     calendar
    -0.69
     rebirth
    -0.68
     elephant
    -0.68
     renaissance
    -0.68
     booth
    -0.68
    POSITIVE LOGITS
     However
    0.97
     Interestingly
    0.93
    com
    0.92
    org
    0.90
    net
    0.88
    cn
    0.87
     Meanwhile
    0.86
     Needless
    0.85
     Asked
    0.85
     Apparently
    0.83
    Activations Density 0.114%

    No Known Activations