© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5389
    Prev
    Next
    INDEX
    Explanations

    words related to computer software and technology

    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
    665
    +0.13
    0.6%
    745
    +0.12
    0.5%
    663
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.13
    0.05
    503
    +0.12
    0.04
    745
    +0.10
    0.00
    Negative Logits
     characteristic
    -0.71
     wont
    -0.68
     marks
    -0.65
     Waiting
    -0.65
     disappearing
    -0.63
     guessing
    -0.62
     Sunshine
    -0.61
     moments
    -0.61
     Amph
    -0.61
     endings
    -0.60
    POSITIVE LOGITS
    ulate
    1.39
    imize
    1.35
    ify
    1.35
    ize
    1.34
    itate
    1.33
    igrate
    1.30
    uate
    1.25
    rouse
    1.24
    activate
    1.23
    strate
    1.22
    Activations Density 0.270%

    No Known Activations