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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 12327
    Prev
    Next
    INDEX
    Explanations

    mentions of social media platforms like Facebook and Twitter

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    481
    +0.15
    0.7%
    297
    +0.12
    0.5%
    447
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.15
    0.04
    732
    +0.12
    0.03
    546
    +0.10
    0.04
    Negative Logits
    sole
    -0.75
     defects
    -0.71
     unborn
    -0.68
    hani
    -0.68
     recoil
    -0.68
    uties
    -0.68
    idates
    -0.67
    abilities
    -0.65
    older
    -0.65
    emen
    -0.64
    POSITIVE LOGITS
     Twitter
    1.20
     Youtube
    1.15
     Facebook
    1.15
     Instagram
    1.14
    Twitter
    1.12
     YouTube
    1.10
     Internet
    1.09
     LinkedIn
    1.07
    acebook
    1.06
     Tumblr
    1.05
    Activations Density 0.242%

    No Known Activations