© 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. 24030
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "met"

    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
    314
    +0.13
    0.6%
    464
    +0.12
    0.5%
    420
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.13
    0.01
    252
    +0.12
    0.01
    456
    +0.11
    0.01
    Negative Logits
     Mutual
    -0.67
    ãģį
    -0.62
    FE
    -0.61
    perm
    -0.61
     Toro
    -0.60
    GBT
    -0.59
    BIP
    -0.58
     Behavioral
    -0.56
     CARD
    -0.56
     Mayo
    -0.55
    POSITIVE LOGITS
    ropolitan
    1.34
    eor
    1.34
    amorph
    1.18
    allic
    1.17
    rics
    1.08
    ropolis
    0.98
    imet
    0.98
    rique
    0.97
    ric
    0.95
    adata
    0.93
    Activations Density 0.005%

    No Known Activations