© 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 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. 10495
    Prev
    Next
    INDEX
    Explanations

    organizations, locations, and current affairs mentioned in articles

    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
    +0.20
    0.9%
    447
    +0.17
    0.8%
    692
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    267
    +0.20
    0.06
    186
    +0.17
    0.05
    241
    +0.11
    0.05
    Negative Logits
    range
    -0.75
     Adin
    -0.73
    nothing
    -0.67
    none
    -0.65
    sit
    -0.63
    bearing
    -0.62
    interstitial
    -0.61
    depending
    -0.61
    because
    -0.60
    req
    -0.58
    POSITIVE LOGITS
     publishes
    1.17
     Ltd
    1.02
     understands
    1.00
     expects
    0.97
     welcomes
    0.97
     Editor
    0.96
     recommends
    0.93
     Presents
    0.92
     believes
    0.91
     strives
    0.91
    Activations Density 0.295%

    No Known Activations