© 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. 19637
    Prev
    Next
    INDEX
    Explanations

    differences or conflicts between entities

    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
    608
    +0.14
    0.6%
    549
    +0.13
    0.6%
    476
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.14
    0.04
    549
    +0.13
    0.03
    476
    +0.10
    0.02
    Negative Logits
    inventoryQuantity
    -0.81
    OGR
    -0.81
    nit
    -0.80
    unc
    -0.78
     teasp
    -0.77
    raq
    -0.73
    pletion
    -0.73
    ickr
    -0.71
    pleted
    -0.70
    gow
    -0.69
    POSITIVE LOGITS
     sexes
    1.09
     combatants
    0.97
     genders
    0.96
     factions
    0.94
     Israelis
    0.90
     spouses
    0.87
     parties
    0.85
     halves
    0.81
     Kore
    0.80
     sides
    0.78
    Activations Density 0.049%

    No Known Activations