© 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. 22349
    Prev
    Next
    INDEX
    Explanations

    the word "combined" and its variations, indicating a focus on the concept of combination or collective efforts

    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
    618
    +0.13
    0.6%
    355
    +0.13
    0.6%
    251
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    355
    +0.13
    0.02
    251
    +0.13
    0.02
    599
    +0.10
    0.02
    Negative Logits
    keeper
    -0.88
    keepers
    -0.81
    otle
    -0.77
    writers
    -0.77
    cott
    -0.77
    posts
    -0.76
    geons
    -0.76
    holes
    -0.75
     Passage
    -0.74
    guards
    -0.74
    POSITIVE LOGITS
     effort
    0.73
    ively
    0.71
    ãĤ¤ãĥĪ
    0.70
     sexes
    0.69
    iliary
    0.65
     totals
    0.65
     oppos
    0.65
     efforts
    0.64
     sum
    0.63
    ivia
    0.62
    Activations Density 0.021%

    No Known Activations