© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 24501
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "ur."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    373
    +0.13
    0.6%
    727
    +0.12
    0.6%
    543
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.13
    0.03
    406
    +0.12
    0.02
    373
    +0.10
    -0.01
    Negative Logits
    otle
    -0.75
    ept
    -0.66
     Opportunity
    -0.64
    ophers
    -0.63
     Schultz
    -0.63
    aan
    -0.63
     Clarkson
    -0.61
     Feder
    -0.60
     Citation
    -0.59
    eden
    -0.59
    POSITIVE LOGITS
    geon
    1.29
    geons
    1.22
    rences
    1.04
    thur
    1.02
    andom
    0.99
     Rahman
    0.94
    ricane
    0.89
    ricanes
    0.89
    geoning
    0.89
    rr
    0.86
    Activations Density 0.028%

    No Known Activations