© 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 1536
    9. 8-RES_FS1536-JB
    11. 1051
    Prev
    Next
    INDEX
    Explanations

    phrases related to controversial political topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    223
    +0.14
    0.6%
    512
    +0.12
    0.5%
    13
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.14
    0.09
    279
    +0.12
    0.09
    13
    +0.11
    0.10
    Negative Logits
    iba
    -0.81
    uffle
    -0.79
    aten
    -0.76
    asha
    -0.66
    gra
    -0.64
    nel
    -0.64
     suicides
    -0.63
    aters
    -0.62
    indu
    -0.62
    ami
    -0.62
    POSITIVE LOGITS
     opportunity
    1.05
     chance
    1.01
     thumbs
    0.95
     choice
    0.91
     insight
    0.89
     berth
    0.88
     assurance
    0.87
     permission
    0.87
     assurances
    0.83
     latitude
    0.81
    Activations Density 2.290%

    No Known Activations