© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 220
    Prev
    Next
    INDEX
    Explanations

    words related to social media platforms and activism

    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
    247
    +0.12
    0.6%
    609
    +0.11
    0.5%
    343
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.12
    0.05
    343
    +0.11
    0.05
    508
    +0.11
    0.05
    Negative Logits
    nces
    -0.85
    heny
    -0.69
    cised
    -0.69
    lass
    -0.63
    rosc
    -0.62
    ved
    -0.62
     Croat
    -0.62
    inence
    -0.62
    ptin
    -0.61
    Äĩ
    -0.61
    POSITIVE LOGITS
     Messenger
    1.01
    nect
    0.93
    username
    0.90
     Live
    0.83
     Pages
    0.81
    acebook
    0.81
     Username
    0.77
    LinkedIn
    0.73
    Friends
    0.73
     Ads
    0.72
    Activations Density 0.379%

    No Known Activations