© 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. 45721
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the."

    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
    393
    +0.15
    0.7%
    374
    +0.11
    0.5%
    379
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    374
    +0.15
    0.02
    379
    +0.11
    0.03
    554
    +0.10
    0.01
    Negative Logits
    ambo
    -0.93
    abul
    -0.78
    ndra
    -0.76
    gb
    -0.75
    tions
    -0.74
    aza
    -0.71
    Operation
    -0.71
    ioned
    -0.70
    Lago
    -0.68
    -+-+
    -0.68
    POSITIVE LOGITS
     brunt
    1.23
     plunge
    1.05
     reins
    1.02
     initiative
    1.00
     blame
    0.94
     same
    0.91
     opportunity
    0.89
     responsibility
    0.89
     slightest
    0.89
     cues
    0.89
    Activations Density 0.029%

    No Known Activations