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 3072
    5. 8-RES_FS3072-JB
    6. 1028
    Prev
    Next
    INDEX
    Explanations

    the economic implications of legalizing marijuana

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    +0.16
    0.7%
    218
    +0.10
    0.5%
    408
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    703
    +0.16
    0.07
    408
    +0.10
    0.10
    218
    +0.10
    0.06
    Negative Logits
    apest
    -0.83
    aurus
    -0.81
    ippi
    -0.80
    ppa
    -0.78
    arc
    -0.77
    emo
    -0.76
    onyms
    -0.74
    enf
    -0.73
    arta
    -0.71
    oku
    -0.70
    POSITIVE LOGITS
     exposure
    0.98
     ingest
    0.95
     combining
    0.90
     ingestion
    0.89
     globalization
    0.88
     untreated
    0.87
     inaction
    0.86
     prolonged
    0.85
     consuming
    0.83
     subtract
    0.81
    Activations Density 1.625%

    No Known Activations