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. 140
    Prev
    Next
    INDEX
    Explanations

    information related to politics, global events, and ethical/moral issues

    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
    31
    +0.10
    0.5%
    16
    +0.09
    0.4%
    444
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.10
    0.13
    542
    +0.09
    0.09
    274
    +0.09
    0.08
    Negative Logits
     inver
    -0.77
    ilet
    -0.69
    dry
    -0.68
    itch
    -0.64
    waters
    -0.63
    cise
    -0.62
    itches
    -0.61
    flix
    -0.58
    vernight
    -0.56
     spoilers
    -0.56
    POSITIVE LOGITS
     incurred
    1.06
     accrued
    1.06
     bestowed
    1.04
     afforded
    1.01
     emanating
    0.94
     wrought
    0.91
     arising
    0.89
     undertaken
    0.89
     generated
    0.88
     inflicted
    0.87
    Activations Density 2.760%

    No Known Activations