© 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 EvalsExportsinterp-engineNEWAPI 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. 5563
    Prev
    Next
    INDEX
    Explanations

    links in social media posts

    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
    314
    +0.13
    0.6%
    640
    +0.13
    0.6%
    435
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.13
    0.03
    313
    +0.13
    0.02
    160
    +0.12
    0.02
    Negative Logits
     Aires
    -0.76
     Pyramid
    -0.74
     Stoke
    -0.68
     Steal
    -0.68
     Salt
    -0.67
     Yale
    -0.65
     Coco
    -0.64
     grate
    -0.64
     Colleges
    -0.63
     Diplom
    -0.63
    POSITIVE LOGITS
    76561
    1.28
    DragonMagazine
    1.13
    detail
    1.09
    10000
    1.05
    tnc
    1.00
    pmwiki
    0.98
    album
    0.94
    posts
    0.93
    default
    0.92
    details
    0.90
    Activations Density 0.021%

    No Known Activations