© 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. 45785
    Prev
    Next
    INDEX
    Explanations

    terms related to legal issues and political conflicts

    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
    480
    +0.15
    0.7%
    157
    +0.11
    0.5%
    51
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.15
    0.05
    157
    +0.11
    0.04
    390
    +0.11
    0.02
    Negative Logits
     Tycoon
    -0.74
     awoke
    -0.67
    estamp
    -0.66
     woke
    -0.65
    iru
    -0.64
    umbledore
    -0.62
    raph
    -0.61
    oyer
    -0.60
     Abyssal
    -0.58
    ultimate
    -0.57
    POSITIVE LOGITS
     lately
    1.09
     since
    1.04
     numerous
    0.96
     recent
    0.90
     spor
    0.84
     dozens
    0.84
     recently
    0.81
     unsuccessfully
    0.81
     settlements
    0.79
     longstanding
    0.78
    Activations Density 0.475%

    No Known Activations