© 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. 9901
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software updates and events

    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
    +0.26
    1.2%
    739
    +0.12
    0.6%
    530
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.26
    0.05
    308
    +0.12
    0.03
    530
    +0.12
    0.04
    Negative Logits
     answ
    -0.71
     conflic
    -0.70
     undermin
    -0.69
    dyl
    -0.69
     resent
    -0.68
     disg
    -0.68
     incorpor
    -0.68
    etsk
    -0.67
     custod
    -0.66
     conce
    -0.65
    POSITIVE LOGITS
     Overview
    1.01
     Edition
    0.98
     Copyright
    0.98
     Highlights
    0.93
     Version
    0.92
     Quote
    0.92
     Comparison
    0.91
     Featuring
    0.91
     Released
    0.90
     Written
    0.89
    Activations Density 0.347%

    No Known Activations