© 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. 7553
    Prev
    Next
    INDEX
    Explanations

    instances of negation and uncertainty in text

    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
    183
    +0.11
    0.5%
    373
    +0.11
    0.5%
    301
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    221
    +0.11
    0.04
    102
    +0.11
    0.06
    183
    +0.10
    0.04
    Negative Logits
     Saturn
    -0.63
     Beirut
    -0.63
     McDonnell
    -0.62
     Shogun
    -0.62
     Madden
    -0.60
     contrasted
    -0.59
     Ney
    -0.58
     Employee
    -0.58
     hostage
    -0.57
     Rolls
    -0.55
    POSITIVE LOGITS
     thereof
    1.26
     versa
    1.15
    existent
    0.94
     thereto
    0.89
    .?
    0.86
    .","
    0.85
    chal
    0.78
    abouts
    0.76
    hin
    0.75
    ilater
    0.72
    Activations Density 0.437%

    No Known Activations