© 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 24576
    5. 8-RES_FS24576-JB
    6. 6656
    Prev
    Next
    INDEX
    Explanations

    words related to instructions and steps

    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
    641
    +0.11
    0.5%
    755
    +0.10
    0.4%
    367
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    231
    +0.11
    0.04
    641
    +0.10
    0.04
    498
    +0.09
    0.04
    Negative Logits
     beg
    -0.63
    Eat
    -0.62
    pron
    -0.60
     deserves
    -0.60
    è¦ļéĨĴ
    -0.59
    izzle
    -0.59
    çļĦ
    -0.56
    intern
    -0.56
    Naz
    -0.55
    bleacher
    -0.55
    POSITIVE LOGITS
     example
    1.75
     instance
    1.55
    cing
    1.34
    bidden
    1.20
     Example
    1.18
     comparison
    1.16
    ced
    1.11
     purposes
    1.08
     starters
    1.05
    example
    1.03
    Activations Density 0.065%

    No Known Activations