© 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. 18464
    Prev
    Next
    INDEX
    Explanations

    information related to software development, specifically modules and coding tutorials

    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
    481
    +0.20
    0.9%
    447
    +0.13
    0.6%
    640
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.20
    0.07
    6
    +0.13
    0.06
    176
    +0.12
    0.03
    Negative Logits
     outraged
    -0.80
     offended
    -0.80
     champ
    -0.77
     horrified
    -0.76
     angered
    -0.72
     snatched
    -0.71
     dismay
    -0.71
     guards
    -0.70
     anytime
    -0.70
     distraught
    -0.69
    POSITIVE LOGITS
     Introduction
    1.41
    Introduction
    1.40
     Conclusion
    1.38
    Understanding
    1.23
     Understanding
    1.21
     Principles
    1.10
     Lessons
    1.10
     Functions
    1.09
     Definitions
    1.09
     Basics
    1.08
    Activations Density 0.238%

    No Known Activations