© 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. 37481
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "order" and "dreams" within societal and economic contexts

    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
    481
    +0.25
    1.2%
    447
    +0.16
    0.8%
    225
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.25
    0.05
    225
    +0.16
    0.04
    431
    +0.11
    0.03
    Negative Logits
     obser
    -0.84
    ãģį
    -0.65
    é£
    -0.64
     pert
    -0.64
     manag
    -0.63
    vice
    -0.62
    inventoryQuantity
    -0.61
     confir
    -0.60
     trave
    -0.59
    qualified
    -0.58
    POSITIVE LOGITS
    âĦ¢
    0.91
     Era
    0.88
     era
    0.81
    eers
    0.80
     continuum
    0.75
     Tradition
    0.74
    ;;;;;;;;;;;;
    0.73
     itself
    0.73
     Syndrome
    0.73
    icist
    0.72
    Activations Density 0.145%

    No Known Activations