© 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. 195
    Prev
    Next
    INDEX
    Explanations

    JavaScript code snippets for creating image galleries

    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
    737
    +0.12
    0.5%
    404
    +0.11
    0.5%
    684
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    684
    +0.12
    0.02
    111
    +0.11
    0.02
    482
    +0.11
    0.02
    Negative Logits
    406
    -0.88
     Soda
    -0.88
     Colo
    -0.84
     Cipher
    -0.80
     Cic
    -0.79
     Chic
    -0.77
     Mex
    -0.75
     Chip
    -0.74
     406
    -0.74
    tc
    -0.73
    POSITIVE LOGITS
    2017
    1.09
    UK
    0.92
    uk
    0.88
     2017
    0.87
    17
    0.86
    ouk
    0.86
     Corbyn
    0.79
    roy
    0.78
    kens
    0.74
    umat
    0.73
    Activations Density 0.086%

    No Known Activations