© 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. 8875
    Prev
    Next
    INDEX
    Explanations

    food-related terms and ingredients, particularly for cooking and pairing with different foods

    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
    490
    +0.11
    0.5%
    517
    +0.10
    0.5%
    704
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    556
    +0.11
    0.05
    711
    +0.10
    0.03
    490
    +0.10
    0.05
    Negative Logits
    rooms
    -0.91
    liners
    -0.85
     channels
    -0.83
    places
    -0.82
    lees
    -0.81
    yards
    -0.80
    builders
    -0.78
    units
    -0.75
    ages
    -0.74
     avenues
    -0.74
    POSITIVE LOGITS
     clone
    0.94
     sticker
    0.92
     endorsement
    0.88
     sweater
    0.86
    ussian
    0.84
    esque
    0.83
     wrapper
    0.81
     inhibitor
    0.80
     sized
    0.80
     jumper
    0.80
    Activations Density 0.436%

    No Known Activations