© 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 49152
    9. 8-RES_FS49152-JB
    11. 41519
    Prev
    Next
    INDEX
    Explanations

    phrases related to funding sources and financial contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    608
    +0.10
    0.5%
    292
    +0.09
    0.4%
    614
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.10
    0.04
    385
    +0.09
    0.03
    362
    +0.08
    0.03
    Negative Logits
    terness
    -0.90
    olit
    -0.80
    endon
    -0.80
    icter
    -0.75
    ensis
    -0.75
    inction
    -0.74
    hent
    -0.72
    mbuds
    -0.72
    perfect
    -0.71
    faced
    -0.71
    POSITIVE LOGITS
     donations
    1.38
     taxpayers
    1.29
     donors
    1.28
     royalties
    1.25
     taxpayer
    1.21
     funds
    1.19
     coffers
    1.19
     philanthrop
    1.16
     reimburse
    1.15
     donation
    1.14
    Activations Density 0.073%

    No Known Activations