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. 23228
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to specific dates or times

    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
    763
    +0.10
    0.5%
    477
    +0.10
    0.5%
    32
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    493
    +0.10
    0.02
    227
    +0.10
    0.01
    734
    +0.10
    0.02
    Negative Logits
    kas
    -0.79
     Invaders
    -0.76
    uka
    -0.73
     Knight
    -0.71
     Invention
    -0.70
    ISA
    -0.69
    ige
    -0.69
    iman
    -0.69
    ibal
    -0.66
     MU
    -0.65
    POSITIVE LOGITS
    10
    1.49
     10
    1.17
    1027
    0.97
    1016
    0.94
    11
    0.94
     1070
    0.92
    110
    0.92
    105
    0.91
    1100
    0.90
    1024
    0.90
    Activations Density 0.060%

    No Known Activations