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 1536
    5. 8-RES_FS1536-JB
    6. 160
    Prev
    Next
    INDEX
    Explanations

    actions related to protection, sacrifice, and rescue

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    74
    +0.10
    0.5%
    669
    +0.10
    0.4%
    97
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.10
    0.09
    362
    +0.10
    0.11
    97
    +0.09
    0.06
    Negative Logits
    gebra
    -0.69
     accelerator
    -0.68
     solicitation
    -0.67
    venants
    -0.66
     slang
    -0.65
     Wave
    -0.63
    OUT
    -0.63
    visual
    -0.62
     quizz
    -0.62
     Analy
    -0.62
    POSITIVE LOGITS
     dignity
    1.11
     unborn
    1.05
     humankind
    1.05
     taxpayers
    1.03
     endangered
    0.99
     grandchildren
    0.97
     livelihood
    0.97
     innoc
    0.96
     mankind
    0.95
     innocent
    0.94
    Activations Density 3.007%

    No Known Activations