© 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 49152
    9. 8-RES_FS49152-JB
    11. 37549
    Prev
    Next
    INDEX
    Explanations

    words related to verbs and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    559
    +0.11
    0.5%
    106
    +0.10
    0.5%
    281
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.02
    659
    +0.10
    0.02
    373
    +0.10
    -0.01
    Negative Logits
    wives
    -1.04
    earchers
    -0.79
    ascript
    -0.71
     vets
    -0.66
    itionally
    -0.65
    yards
    -0.65
    arers
    -0.64
    igators
    -0.63
    drm
    -0.63
    thirds
    -0.62
    POSITIVE LOGITS
    sson
    1.00
    owicz
    0.81
     Klopp
    0.70
     Klu
    0.64
     è£ıè
    0.64
     TAMADRA
    0.63
     Hou
    0.62
     Kore
    0.61
     Deb
    0.61
     Dortmund
    0.61
    Activations Density 0.024%

    No Known Activations