© 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 24576
    9. 8-RES_FS24576-JB
    11. 12043
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific details or considerations that are considered significant or valuable in a context

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    737
    +0.17
    0.8%
    101
    +0.10
    0.5%
    227
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.17
    0.05
    679
    +0.10
    0.04
    451
    +0.10
    0.03
    Negative Logits
    igham
    -0.79
    flat
    -0.75
     vomiting
    -0.71
     Carbuncle
    -0.67
     closet
    -0.66
    osa
    -0.66
     vomit
    -0.65
     Wonderland
    -0.64
     sweats
    -0.64
    inis
    -0.62
    POSITIVE LOGITS
     viz
    0.88
     importance
    0.75
    rients
    0.75
     safegu
    0.75
     protecting
    0.74
     ensuring
    0.74
    important
    0.73
     crucial
    0.72
     namely
    0.70
     vital
    0.69
    Activations Density 0.219%

    No Known Activations