© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 37522
    Prev
    Next
    INDEX
    Explanations

    pronouns and related verb forms, indicating discussions about people and their actions

    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
    497
    +0.10
    0.5%
    309
    +0.09
    0.4%
    83
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.10
    0.03
    566
    +0.09
    0.03
    551
    +0.09
    0.03
    Negative Logits
    artisan
    -0.70
    emetery
    -0.67
    Americ
    -0.66
     cess
    -0.64
    noon
    -0.63
    itary
    -0.62
    rontal
    -0.62
     Seat
    -0.59
    hma
    -0.57
    tur
    -0.57
    POSITIVE LOGITS
     boils
    0.82
     learnt
    0.81
     Learned
    0.80
     lacks
    0.74
     learned
    0.74
     REALLY
    0.72
     lacked
    0.72
     happened
    0.72
     happens
    0.69
     learns
    0.69
    Activations Density 0.043%

    No Known Activations