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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9425
    Prev
    Next
    INDEX
    Explanations

    mentions of specific programming languages and related tools

    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
    447
    +0.18
    0.8%
    481
    +0.13
    0.6%
    359
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.18
    0.02
    359
    +0.13
    0.02
    547
    +0.10
    0.02
    Negative Logits
     Anthem
    -0.74
    interstitial
    -0.74
    aughters
    -0.67
    rating
    -0.67
     Gallup
    -0.67
     Hilton
    -0.66
    hin
    -0.66
    hower
    -0.65
     Tanz
    -0.64
     Ezek
    -0.63
    POSITIVE LOGITS
     bindings
    1.11
    Script
    1.05
     syntax
    1.02
     programmers
    1.01
     Lisp
    1.00
     equivalents
    0.97
     Programming
    0.92
     compiler
    0.92
    API
    0.91
     implementations
    0.90
    Activations Density 0.062%

    No Known Activations