© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 24576
    9. 8-RES_FS24576-JB
    11. 9037
    Prev
    Next
    INDEX
    Explanations

    phrases related to international summits or meetings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    447
    +0.20
    0.9%
    288
    +0.16
    0.8%
    526
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    677
    +0.20
    0.02
    391
    +0.16
    0.01
    500
    +0.10
    0.02
    Negative Logits
    served
    -0.72
    lean
    -0.70
    effic
    -0.68
    enfranch
    -0.67
     Mechdragon
    -0.65
    ourke
    -0.65
    avery
    -0.64
    yright
    -0.63
    yne
    -0.62
     bleach
    -0.62
    POSITIVE LOGITS
     summit
    1.01
     convened
    0.88
     attendees
    0.84
     Summit
    0.84
     organisers
    0.77
     chaired
    0.77
    iership
    0.75
     meetings
    0.72
     session
    0.72
     planners
    0.69
    Activations Density 0.025%

    No Known Activations