© 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. 1071
    Prev
    Next
    INDEX
    Explanations

    actions related to offering or providing help

    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
    504
    +0.11
    0.5%
    718
    +0.10
    0.5%
    327
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    327
    +0.11
    0.06
    504
    +0.10
    0.06
    695
    +0.10
    0.06
    Negative Logits
    theless
    -0.79
    iu
    -0.72
    meat
    -0.69
    rencies
    -0.62
    posure
    -0.61
    ata
    -0.61
    é¾
    -0.59
    Pict
    -0.59
    amba
    -0.58
     Hebdo
    -0.58
    POSITIVE LOGITS
     alleviate
    1.00
     facilitate
    0.97
     stabilize
    0.89
     improve
    0.88
     organize
    0.87
    fully
    0.87
     relieve
    0.85
     propel
    0.85
     solve
    0.85
     tremendously
    0.84
    Activations Density 1.245%

    No Known Activations