© 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. 41138
    Prev
    Next
    INDEX
    Explanations

    the word "solely" indicating exclusivity or limitation

    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
    737
    +0.11
    0.5%
    289
    +0.09
    0.4%
    441
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.11
    0.02
    441
    +0.09
    0.01
    569
    +0.09
    0.01
    Negative Logits
     Nurs
    -0.75
    ctl
    -0.64
    LI
    -0.64
     Mushroom
    -0.63
    lyn
    -0.63
    most
    -0.62
    shift
    -0.62
     Neighbor
    -0.61
     Archbishop
    -0.61
    dl
    -0.61
    POSITIVE LOGITS
     focused
    0.94
     reliant
    0.87
     relying
    0.86
     foc
    0.86
     responsible
    0.85
     rely
    0.74
     catering
    0.73
     focusing
    0.72
     relied
    0.71
     solely
    0.69
    Activations Density 0.010%

    No Known Activations