© 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 3072
    9. 8-RES_FS3072-JB
    11. 757
    Prev
    Next
    INDEX
    Explanations

    phrases related to critical situations or conflicts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    373
    +0.14
    0.7%
    209
    +0.10
    0.5%
    57
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.14
    -0.00
    373
    +0.10
    -0.09
    284
    +0.10
    0.09
    Negative Logits
    upt
    -0.69
    aneously
    -0.62
    bj
    -0.62
    AMY
    -0.62
    photos
    -0.60
    nces
    -0.60
    ILY
    -0.60
    IUM
    -0.59
    anian
    -0.58
    istar
    -0.57
    POSITIVE LOGITS
     proverbial
    0.84
     sleeve
    0.69
     sleeves
    0.67
     mouth
    0.64
     roses
    0.64
     hat
    0.64
     glove
    0.63
     lettuce
    0.61
     bisc
    0.60
     riches
    0.60
    Activations Density 3.218%

    No Known Activations