© 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 768
    9. 8-RES_FS768-JB
    11. 516
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals and their actions or situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    37
    +0.11
    0.5%
    499
    +0.11
    0.5%
    69
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    499
    +0.11
    0.11
    55
    +0.11
    0.18
    668
    +0.10
    0.10
    Negative Logits
    selves
    -0.93
     unison
    -0.86
     selves
    -0.84
    results
    -0.69
    Recommend
    -0.67
     asses
    -0.66
    OTAL
    -0.66
     collective
    -0.66
     Consumers
    -0.65
    mination
    -0.65
    POSITIVE LOGITS
     himself
    1.66
     Himself
    1.19
     assassinated
    1.06
     his
    1.02
     herself
    0.97
     famously
    0.94
     personally
    0.94
    enegger
    0.89
     resigned
    0.88
     persona
    0.88
    Activations Density 8.478%

    No Known Activations