© 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 12288
    9. 8-RES_FS12288-JB
    11. 1588
    Prev
    Next
    INDEX
    Explanations

    phrases related to organization and distribution

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    619
    +0.13
    0.6%
    656
    +0.10
    0.5%
    390
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    619
    +0.13
    0.05
    268
    +0.10
    0.02
    390
    +0.10
    0.03
    Negative Logits
    tek
    -0.77
    ibur
    -0.77
    acers
    -0.71
    ãĤ®
    -0.70
    acea
    -0.66
    KN
    -0.65
     Fitzgerald
    -0.64
    Ire
    -0.64
     Muse
    -0.63
    arag
    -0.63
    POSITIVE LOGITS
     geographically
    1.08
     unequal
    1.03
     clust
    1.02
     grouping
    1.02
     allocation
    1.01
     arrangement
    0.98
     evenly
    0.98
     overlapping
    0.97
     hierarch
    0.95
     tenancy
    0.94
    Activations Density 0.929%

    No Known Activations