Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23079
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or characters in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    659
    +0.13
    0.6%
    314
    +0.10
    0.5%
    481
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.05
    284
    +0.10
    0.04
    326
    +0.10
    0.04
    Negative Logits
     millenn
    -0.81
     transact
    -0.75
     closures
    -0.73
     merit
    -0.72
     increment
    -0.71
     textbooks
    -0.71
     UNESCO
    -0.71
     readiness
    -0.71
     foundations
    -0.71
     credential
    -0.70
    POSITIVE LOGITS
    666
    1.09
    Gaming
    1.09
    bear
    1.08
    pie
    1.07
    guy
    1.05
    ragon
    1.02
    420
    1.01
    abbit
    1.00
    Magikarp
    0.99
     Profile
    0.98
    Activations Density 0.179%

    No Known Activations