© 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 EvalsExportsinterp-engineNEWAPI 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. 17154
    Prev
    Next
    INDEX
    Explanations

    descriptions related to food and cooking

    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
    481
    +0.11
    0.5%
    289
    +0.11
    0.5%
    393
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.11
    0.03
    234
    +0.11
    0.03
    608
    +0.10
    0.03
    Negative Logits
    NPR
    -0.80
    raviolet
    -0.74
    ©¶æ¥µ
    -0.73
    Enlarge
    -0.72
    ©¶æ
    -0.72
    wake
    -0.72
    ħĭ
    -0.69
    jong
    -0.69
    si
    -0.68
    Ĥİ
    -0.66
    POSITIVE LOGITS
     surprises
    1.13
     contradictions
    0.96
     goodies
    0.88
     holes
    0.84
     excitement
    0.83
     intrigue
    0.81
     curiosity
    0.80
     passion
    0.79
     distractions
    0.79
     emotion
    0.79
    Activations Density 0.081%

    No Known Activations