© 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 24576
    9. 8-RES_FS24576-JB
    11. 12106
    Prev
    Next
    INDEX
    Explanations

    instances of the word "test."

    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
    329
    +0.10
    0.5%
    534
    +0.09
    0.4%
    641
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    641
    +0.10
    0.03
    362
    +0.09
    0.03
    587
    +0.09
    0.03
    Negative Logits
    CHAPTER
    -0.78
    SOURCE
    -0.76
     Deaths
    -0.73
     mourn
    -0.72
     mourning
    -0.66
    \">
    -0.66
    MpServer
    -0.65
     regrets
    -0.65
    Sad
    -0.65
    RIP
    -0.64
    POSITIVE LOGITS
     hypotheses
    1.17
     feasibility
    1.01
     viability
    0.94
     readiness
    0.93
    worthiness
    0.90
     hypothesis
    0.90
     prototypes
    0.88
     experimental
    0.83
     simulated
    0.80
     efficacy
    0.78
    Activations Density 0.202%

    No Known Activations