© 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. 4720
    Prev
    Next
    INDEX
    Explanations

    references to historical events or scientific concepts related to the universe

    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
    325
    +0.11
    0.5%
    598
    +0.11
    0.5%
    430
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.07
    288
    +0.11
    0.07
    574
    +0.10
    0.05
    Negative Logits
    terday
    -0.90
     sidel
    -0.68
    etheless
    -0.68
    ĪĴ
    -0.65
     haste
    -0.64
     dent
    -0.63
     profiling
    -0.63
    quartered
    -0.62
     separat
    -0.61
     hepat
    -0.61
    POSITIVE LOGITS
     Bureau
    1.03
     Bowl
    1.02
     Council
    1.01
     Era
    1.00
     Committee
    0.97
     Room
    0.97
     Commission
    0.96
     Chamber
    0.95
     Office
    0.93
     Museum
    0.92
    Activations Density 0.295%

    No Known Activations