© 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. 13525
    Prev
    Next
    INDEX
    Explanations

    organizations, projects and initiatives related to global participation, financial stability, and community efforts

    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
    447
    +0.39
    1.9%
    481
    +0.29
    1.5%
    232
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.39
    0.08
    659
    +0.29
    0.06
    481
    +0.10
    0.06
    Negative Logits
     congr
    -0.69
     myster
    -0.65
     weap
    -0.63
    $$$$
    -0.62
     livest
    -0.61
     cele
    -0.61
     sacrific
    -0.61
     notor
    -0.60
     ingred
    -0.60
     skelet
    -0.59
    POSITIVE LOGITS
    lambda
    0.66
     consists
    0.66
    raq
    0.64
    inar
    0.62
    halla
    0.61
    idine
    0.59
    ind
    0.59
    bots
    0.59
    oval
    0.57
    atech
    0.57
    Activations Density 0.302%

    No Known Activations