© 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 3072
    9. 8-RES_FS3072-JB
    11. 81
    Prev
    Next
    INDEX
    Explanations

    ice-related terms along with terms related to sports teams and players

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    +0.17
    0.8%
    422
    +0.12
    0.6%
    327
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.14
    564
    +0.12
    0.10
    737
    +0.11
    0.10
    Negative Logits
    laus
    -0.82
    anson
    -0.74
    oras
    -0.69
    olver
    -0.65
    iago
    -0.64
    ommod
    -0.64
    rosso
    -0.62
    auts
    -0.61
    oris
    -0.60
    emn
    -0.60
    POSITIVE LOGITS
     unnoticed
    0.84
     aisle
    0.82
     doorstep
    0.81
     periphery
    0.79
     whenever
    0.76
    waves
    0.76
    steps
    0.73
     somewhere
    0.73
     undet
    0.72
     courtyard
    0.70
    Activations Density 1.622%

    No Known Activations