© 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 3072
    9. 8-RES_FS3072-JB
    11. 794
    Prev
    Next
    INDEX
    Explanations

    names of people involved in legal matters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    240
    +0.12
    0.5%
    232
    +0.11
    0.5%
    688
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.12
    659
    +0.11
    0.11
    701
    +0.10
    0.09
    Negative Logits
     mosqu
    -0.79
     peac
    -0.73
    e
    -0.69
    eer
    -0.66
    OSP
    -0.65
    BALL
    -0.64
    ccording
    -0.63
     resil
    -0.60
     plague
    -0.60
     puzz
    -0.60
    POSITIVE LOGITS
    ée
    0.90
    glas
    0.90
    ruary
    0.87
    geons
    0.85
    anski
    0.84
    enegger
    0.84
    acity
    0.84
    mann
    0.84
    ologist
    0.84
    kson
    0.83
    Activations Density 0.767%

    No Known Activations