© 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. 65
    Prev
    Next
    INDEX
    Explanations

    information related to international and political events or incidents

    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
    640
    +0.30
    1.5%
    160
    +0.15
    0.8%
    442
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.30
    0.25
    442
    +0.15
    0.23
    160
    +0.14
    0.23
    Negative Logits
     waterfall
    -0.81
     casc
    -0.77
     bear
    -0.76
     dece
    -0.75
     commissions
    -0.74
     regener
    -0.73
     bubble
    -0.73
     ability
    -0.73
    ©¶æ
    -0.72
     dra
    -0.72
    POSITIVE LOGITS
    However
    1.72
    According
    1.71
    Asked
    1.69
    Meanwhile
    1.67
    Advertisement
    1.64
    Among
    1.62
    While
    1.61
    But
    1.59
    Related
    1.58
    Although
    1.57
    Activations Density 1.178%

    No Known Activations