© 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. 1571
    Prev
    Next
    INDEX
    Explanations

    Proper nouns, potentially names or locations

    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
    481
    +0.12
    0.6%
    506
    +0.12
    0.5%
    239
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.06
    659
    +0.12
    0.05
    588
    +0.09
    0.04
    Negative Logits
     PAR
    -0.79
    س
    -0.77
     SOU
    -0.77
     Beats
    -0.77
     OCT
    -0.75
     IX
    -0.75
     Panc
    -0.72
     DOS
    -0.71
     davidjl
    -0.70
     +++
    -0.68
    POSITIVE LOGITS
    er
    1.41
    erm
    1.28
    ers
    1.26
    ER
    1.18
    eral
    1.16
    eric
    1.15
    ership
    1.12
    eri
    1.10
    ern
    1.09
    imer
    1.09
    Activations Density 0.288%

    No Known Activations