© 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. 1380
    Prev
    Next
    INDEX
    Explanations

    specific patterns of characters, likely related to code or file information

    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
    176
    +0.12
    0.5%
    314
    +0.11
    0.5%
    160
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.12
    0.03
    176
    +0.11
    0.02
    314
    +0.11
    0.00
    Negative Logits
     Luffy
    -0.73
     Brotherhood
    -0.72
     Garry
    -0.71
     Bucks
    -0.71
     Anglic
    -0.66
     Pennsylvania
    -0.66
     Bian
    -0.65
     Hawk
    -0.65
     Wolverine
    -0.64
     Ridley
    -0.64
    POSITIVE LOGITS
    output
    1.06
    price
    1.02
    description
    1.00
    ItemImage
    1.00
    thro
    1.00
    headers
    0.98
    Attributes
    0.97
    date
    0.97
    max
    0.97
    text
    0.96
    Activations Density 0.048%

    No Known Activations