© 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. 4317
    Prev
    Next
    INDEX
    Explanations

    platforms where downloadable content (DLC) is available

    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
    3
    +0.11
    0.5%
    181
    +0.10
    0.5%
    497
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.11
    0.03
    3
    +0.10
    0.03
    673
    +0.10
    0.03
    Negative Logits
    utenberg
    -0.84
     largeDownload
    -0.77
     rhy
    -0.76
    aez
    -0.74
    jah
    -0.74
     ingred
    -0.73
     undue
    -0.73
     retribution
    -0.72
    usive
    -0.72
     tremend
    -0.71
    POSITIVE LOGITS
     iPad
    1.31
     Desktop
    1.28
     Playstation
    1.25
     iPads
    1.25
     Xbox
    1.25
     iOS
    1.23
     Android
    1.22
     iPhones
    1.21
    Xbox
    1.20
     iPod
    1.19
    Activations Density 0.166%

    No Known Activations