© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 24012
    Prev
    Next
    INDEX
    Explanations

    names or references to people

    oai_token-act-pair · gpt-4o-miniTriggered 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
    373
    +0.12
    0.6%
    556
    +0.10
    0.5%
    55
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.03
    556
    +0.10
    0.02
    232
    +0.10
    0.02
    Negative Logits
    okemon
    -0.70
    llor
    -0.68
     breast
    -0.66
     crochet
    -0.62
     IMAGES
    -0.62
    mong
    -0.61
    iversal
    -0.60
     senseless
    -0.59
    minecraft
    -0.59
     valiant
    -0.58
    POSITIVE LOGITS
    abeth
    1.06
    abet
    0.81
     Musk
    0.78
    otte
    0.76
    phia
    0.71
    ande
    0.71
     guiActiveUn
    0.71
    ée
    0.69
    ias
    0.68
    onde
    0.68
    Activations Density 0.053%

    No Known Activations