© 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 1536
    9. 8-RES_FS1536-JB
    11. 1532
    Prev
    Next
    INDEX
    Explanations

    commands and instructions related to software operations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    41
    +0.10
    0.5%
    8
    +0.10
    0.5%
    204
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    8
    +0.10
    0.10
    498
    +0.10
    0.09
    105
    +0.10
    0.07
    Negative Logits
     Echoes
    -0.68
     enjoyment
    -0.68
    ilty
    -0.68
     discrep
    -0.64
    BuyableInstoreAndOnline
    -0.62
    notations
    -0.62
    stable
    -0.61
    æĪ¦
    -0.59
     lasts
    -0.59
    pport
    -0.58
    POSITIVE LOGITS
     enlist
    0.90
     recourse
    0.85
     devise
    0.85
     resort
    0.82
     devised
    0.78
     resorted
    0.78
    Solution
    0.74
    pmwiki
    0.73
     resorts
    0.72
     preferably
    0.70
    Activations Density 3.436%

    No Known Activations