© 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. 45547
    Prev
    Next
    INDEX
    Explanations

    instances of the word "also."

    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
    679
    +0.16
    0.7%
    128
    +0.12
    0.6%
    481
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    128
    +0.16
    0.04
    596
    +0.12
    0.04
    679
    +0.12
    0.04
    Negative Logits
    ASE
    -0.84
     Ange
    -0.70
    ichen
    -0.65
     Ascension
    -0.65
    agus
    -0.65
     Closing
    -0.62
    itol
    -0.61
    ocene
    -0.60
    athi
    -0.58
    winter
    -0.57
    POSITIVE LOGITS
     includes
    1.18
     incorporates
    1.05
     reflects
    1.02
     coincides
    1.01
     contains
    0.97
     extends
    0.96
     serves
    0.95
     benefited
    0.95
     helps
    0.94
     coincided
    0.94
    Activations Density 0.078%

    No Known Activations