© 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. 10300
    Prev
    Next
    INDEX
    Explanations

    words related to establishments or facilities like "centre", "cluster", and "shop"

    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
    447
    +0.21
    1.0%
    459
    +0.17
    0.8%
    288
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.21
    0.08
    459
    +0.17
    0.07
    11
    +0.12
    0.05
    Negative Logits
    ãĥĥãĥī
    -0.83
    yon
    -0.77
    ãģĦ
    -0.67
    plets
    -0.65
     Marketable
    -0.64
     recoil
    -0.61
     polymer
    -0.61
    ynes
    -0.61
     Rounds
    -0.61
    romy
    -0.60
    POSITIVE LOGITS
     located
    1.06
     situated
    1.04
     staffed
    0.93
     Located
    0.93
     housed
    0.91
     annex
    0.89
     erected
    0.88
     downtown
    0.86
     adjoining
    0.86
     operated
    0.84
    Activations Density 0.319%

    No Known Activations